CN111104797B - Dual-based sequence-to-sequence generation paper network representation learning method - Google Patents

Dual-based sequence-to-sequence generation paper network representation learning method Download PDF

Info

Publication number
CN111104797B
CN111104797B CN201911300281.1A CN201911300281A CN111104797B CN 111104797 B CN111104797 B CN 111104797B CN 201911300281 A CN201911300281 A CN 201911300281A CN 111104797 B CN111104797 B CN 111104797B
Authority
CN
China
Prior art keywords
paper
sequence
node
content
semantic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201911300281.1A
Other languages
Chinese (zh)
Other versions
CN111104797A (en
Inventor
刘杰
李娜
何志成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nankai University
Original Assignee
Nankai University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nankai University filed Critical Nankai University
Priority to CN201911300281.1A priority Critical patent/CN111104797B/en
Publication of CN111104797A publication Critical patent/CN111104797A/en
Application granted granted Critical
Publication of CN111104797B publication Critical patent/CN111104797B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Machine Translation (AREA)

Abstract

A dual sequence-to-sequence generation-based paper network representation learning method, the method comprising: a paper parallel sequence generation section; a paper node identification part (paper content embedding, paper content sequence coding, paper identification sequence generation); a paper content generation part (paper node identification embedding, paper identification sequence coding, paper semantic decoding, paper content generation); and a dual fusion portion. The method integrates content information (namely the topics or abstracts of the papers) of the paper nodes in the paper network and structural information (namely the quotation relations among the papers) of the papers, fuses the two kinds of information more fully through the mutual mapping process of the two kinds of information, and learns the representation of the paper nodes with more meanings. The invention can also continue to decode new text after decoding the text content of the input paper sequence, i.e. new paper content predicted after considering the structure information and content information of the input paper sequence.

Description

Dual-based sequence-to-sequence generation paper network representation learning method
Technical Field
The invention belongs to the technical field of computer application, data mining and network representation learning.
Background
Web-based learning is becoming an increasingly popular research topic because it can be applied in many different downstream tasks. However, because the structure of the network data is very complex, and there is accompanying information, for example, the network data of a large amount of papers includes not only the topic and abstract of the papers, but also the quotation relation information among the papers, and the highly nonlinear information presents challenges for the study of the network representation. In recent years, researchers have made a lot of efforts in the field of network representation learning, have obtained a lot of research results, and have roughly classified network representation learning methods into two categories based on input information of models.
One type is structure-preserving network embedding, such as the classical deep walk [1] model, uses a first-order neighbor structure to perform random walk sampling and learn node characterization based on the resulting node sequence. The node vector model node2vec 2 further provides a random walk algorithm based on a second-order neighbor structure. While Tang Jian et al propose reconstruction losses for first and second order neighbor structures between nodes directly modeled by a large-scale information network embedded model LINE 3. The GraRep model [4] is further generalized to higher-order neighbor structures. However, existing models often require manual specification of structural information to be preserved, such as first order, second order, etc., and still have certain limitations in practical applications.
The other type is network embedding fused with accompanying information, nodes in real network data are often accompanied with information such as labels, types, attributes and the like besides structural information, the accompanying information of the nodes and a topological structure belong to completely different modes, and characteristics of the nodes and high-level semantic relation among the nodes are described from different angles. Based on the deep walk model, liu Zhiyuan and the like of the university of Qinghai introduce node content [5] and label information [6] respectively, so that the performance of node classification tasks is effectively improved. In the embedding research of heterogeneous information network, the models of HINE 7, HNE 8, etc. further consider the types of nodes and edges, so as to model network structure information in finer granularity. However, the existing method lacks of deep mining of node content information and has a certain limitation.
Reference is made to:
[1]Perozzi B,Al-Rfou R,Skiena S.Deepwalk:Online learning of social representations[C]. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2014:701-710.
[2]Grover A,Leskovec J.node2vec:Scalable feature learning for networks[C].Proceedings of the 22th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2016:855–864.
[3]Tang J,Qu M,Wang M,et al.LINE:Large-scale information network embedding[C]. Proceedings of the 24th International Conference on World Wide Web.International World Wide Web Conferences Steering Committee,2015:1067-1077.
[4]Cao S,Lu W,Xu Q.Grarep:Learning graph representations with global structural information[C].Proceedings of the 24th ACM International Conference on Information and Knowledge Management.ACM,2015:891-900.
[5]Yang C,Liu Z,Zhao D,et al.Chang.Network representation learning with rich text information[C].Proceedings of the 24th International Joint Conference on Artificial Intelligence.2015:2111-2117.
[6]Tu C,Zhang W,Liu Z,et al.Max-margin deepwalk:Discriminative learning of network representation[C].Proceedings of the 25th International Joint Conference on Artificial Intelligence.2016:3889-3895.
[7]Huang Z,Mamoulis N.Heterogeneous information network embedding for meta path based proximity[J].arXiv preprint arXiv:1701.05291,2017.
[8]Chang S,Han W,Tang J,et al.Heterogeneous network embedding via deep architectures[C].Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2015:119-128.
disclosure of Invention
The invention aims to solve the problem of effective fusion of complex network structures and paper node content information in a paper network and provides a paper network representation learning method based on dual sequence-to-sequence generation.
The technical proposal of the invention
A dual sequence-to-sequence generation-based paper network representation learning method comprises the following steps:
step 1) paper parallel sequence generation part
Firstly, a random walk method is adopted to walk the paper network to obtain a paper node sequence, and because each paper in the paper network has two types of information including paper numbers and paper text contents, each paper node sequence obtained by walk corresponds to two types of sequences containing different information, namely a paper node identification sequence and a paper node content sequence. The paper node identification sequence comprises the structure information of paper nodes, namely the quotation relation among papers, the paper node content sequence comprises the content information of the papers and part of the inter-paper structure information, and the two sequences are a group of parallel sequences of the papers. Because the two sequences contain different information, the paper network structure information and the paper node content information can be fused through the mutual mapping process of the two sequences.
Step 2) step 2.1) a paper node identification part for implementing mapping from a paper node content sequence to a paper node identification sequence, paper content embedding of the paper node identification part
For the text content of each paper node, firstly, segmenting the text, randomly initializing each word vector, and then capturing the text content information of the paper node by adopting a convolutional neural network (Convolutional Neural Network, CNN), wherein each paper node obtains the corresponding paper node semantic characteristics;
step 2.2) encoding the content sequence of the paper node in the paper node identification section
Coding the paper node content sequence by adopting a bidirectional long-short-Term Memory network (Bidirectional Long Short-Term Memory, bi-LSTM), coding the sequence into a context characteristic representation, and adopting Bi-LSTM to capture forward and reverse information of the paper sequence, wherein a semantic representation vector obtained by coding comprises semantic information of the whole paper node content sequence and structure information among paper nodes implied in the sequence, namely a quotation relation among papers;
step 2.3) generation of the paper node identification sequence of the paper node identification part
Decoding the semantic representation vector obtained by encoding through a Long Short-Term Memory network (LSTM), and mapping the decoded vector into a paper node identification space to complete the generation process of a paper node identification sequence;
step 3) a paper content generation section for implementing mapping from a paper node identification sequence to a paper node content sequence
Step 3.1) paper node identification embedding in paper content Generation section
Adopting an paper node identification embedding layer, and obtaining vector representations of different paper node identifications in a paper node identification sequence by searching an initialization embedding matrix of the paper node;
step 3.2) encoding of the paper node identification sequence of the paper content Generation part
The method comprises the steps of adopting Bi-LSTM to encode an thesis node identification sequence, and encoding the thesis node identification sequence into a context characteristic representation according to sequence structure information among thesis nodes, namely, a quotation relation among papers, and taking the context characteristic representation as input of a subsequent semantic decoding process;
step 3.3) paper semantic decoding of paper content Generation part
Before the content of the paper node is generated, the context characteristic representation is required to be decoded to obtain a paper semantic characteristic sequence which is used for connecting two modal spaces of the paper network structure and the paper node content, and a decoder adopts LSTM;
step 3.4) paper content Generation by the paper content Generation part
Generating text content, namely word sequence, by adopting classical LSTM to semantic characterization of each paper node in the paper semantic feature sequence;
step 4) Dual fusion paper node identification part and paper content generation part
Through sharing of the intermediate hidden layers of the paper node identification part and the paper content generation part, the two parts are simultaneously learned, and the context characteristic representations obtained in the step 2.2) and the step 3.2) are fused in a linear fusion mode.
The sequence-to-sequence model is a translation model that translates one language sequence into another and maps one sequence into another. The sequence-to-sequence model is composed of an encoder and a decoder, wherein an input sequence is firstly encoded into a semantic representation vector, and then the semantic representation vector is decoded into a sequence, so that the mapping from the sequence to the sequence is completed. The sequence-to-sequence model is initially applied to the field of natural language processing for machine translation and abstract generation, is now also applied to the field of network representation learning, fuses different information through a sequence-to-sequence mapping process, and adopts an intermediate result of the model as node representation in a network.
As shown in FIG. 1, the method for learning the paper network representation based on dual sequence-to-sequence generation provided by the invention utilizes the structural relation of paper nodes in the paper network to obtain the paper node sequence by random walk, and each paper node has two modal information: the paper node identification (i.e. the number of the paper) and the paper node content (i.e. the topic or abstract of the paper) finally obtain a group of paper parallel sequences, namely the paper node identification sequence and the corresponding paper node content sequence.
Based on the paper parallel sequences, the invention designs two dual sequence-to-sequence generating parts, namely a paper node identifying part (Node Identification, NI) and a paper content generating part (Content Generation, CG), namely semantic mapping modeling from the paper node content sequence to the paper node identifying sequence and semantic mapping modeling from the paper node identifying sequence to the paper node content sequence. Based on the proposed dual fusion method, the two parts can carry out effective knowledge transfer through a certain fusion strategy. And finally, extracting hidden vectors in intermediate layers of the paper node identification part and the paper content generation part as learned paper node characterization, and applying the hidden vectors to subsequent paper network analysis tasks.
The invention has the advantages and beneficial effects that:
paper node characterization
According to the method, the content information of the paper nodes and the structure information among the paper nodes in the paper network are integrated, the characterization of the paper nodes is learned, and compared with the previous research, the method has the advantages that the content information of the paper nodes and the structure information are fused more fully, and the characterization of the paper nodes is more meaningful.
Paper content prediction
The invention can continue to generate the text content of the new paper by using the trained method, and can continue to decode the content of the new paper after decoding the text content of the input paper sequence in the paper content generation stage of the paper content generation part, namely, consider the structure information and the content information of the input paper sequence and predict the text content of the new paper.
Drawings
FIG. 1 is a flow chart of the present invention learning a representation of a paper node from a paper network.
Fig. 2 is a diagram of a method of performing dual fusion of a paper node recognition part and a paper content generation part of the present invention.
Detailed Description
The invention provides a dual-based sequence-to-sequence generation paper network representation learning method, which is described in detail below with reference to the accompanying drawings and specific implementation.
Example 1:
in order to ensure the normal operation of the system, the invention mainly adopts a deep learning technology to perform paper node characterization learning on a paper network, and in particular implementation, requires that a used computer platform is provided with a memory of not lower than 11G, CPU cores are not lower than 4 and have a main frequency of not lower than 2.6GHz, a GPU environment and a Linux operating system, and necessary software environments such as Python 3.6 and above, pyrach 0.4 and above are installed.
As shown in the method diagram of the dual fusion performed by the paper node identification part and the paper content generation part in fig. 2, a paper network representation learning method based on dual sequence-to-sequence generation comprises the following detailed steps:
step 1) paper parallel sequence generation part
The paper network g= (V, E), V represents the set of all paper nodes in the network,
Figure SMS_1
the edges in the paper network are set and comprise quotation relation information among papers, and if quotation and quotation relation exists among the papers, the edges exist among the papersFor each paper node V e V in the paper network, V is used i Representing the numbering of the nodes of the paper, using v c Content information representing paper nodes. The random walk method is adopted to walk the paper network, and a walk paper node sequence S= { v is obtained 1 ,v 2 ,…,v T For each sequence S, there is a corresponding paper node identification sequence +.>
Figure SMS_2
And the treatise node content order->
Figure SMS_3
The paper node identification sequence and the paper node content sequence are referred to as a set of paper parallel sequences. For example, there is an edge between paper 1 and paper 3, an edge between paper 3 and paper 6, an edge between paper 6 and paper 4, and an edge between paper 4 and paper 9, when random walk, walk from paper 1, walk to paper 3, then walk to paper 6, 4, 9, if the walk length is set to 5, the walk sequence is paper 1→paper 3→paper 6→paper 4→paper 9, then according to the serial number of the paper, the paper node identification sequence 1→3→6→4→9 can be obtained, according to the content information of the paper, the paper node content sequence "data mining#" → "big data#" → "natural language processing" → "text analysis#" web data mining "can be obtained.
Step 2) a paper node identification part step 2.1) a paper node identification part for realizing mapping from a paper node content sequence to a paper node identification sequence:
for the text content of each paper node, firstly, the text is segmented, each word vector is initialized randomly, then CNN is adopted to capture the text content information of the paper node, and each paper node obtains the corresponding paper node semantic characteristics.
Parallel sequences of articles are
Figure SMS_6
wherein />
Figure SMS_9
For the content sequence of the thesis node with the sequence length of n, < >>
Figure SMS_12
The sequence is identified for the paper node with the sequence length of n, and the dictionary is +.>
Figure SMS_5
Randomly initialized word embedding matrix is +.>
Figure SMS_8
Figure SMS_10
For the size of the dictionary, k m Representing the dimension of word embedding, first, a look-up function LookUp is adopted w (. Cndot. Cndot.) will be->
Figure SMS_13
Text content of the t-th paper node in (2)>
Figure SMS_4
Matrix spliced by word embedding vectors>
Figure SMS_7
wherein ut,i For the i-th word in the node content of the t-th paper,>
Figure SMS_11
number of content words for the t-th paper node:
Figure SMS_14
wherein the operator is
Figure SMS_15
Representing the operation of stitching the vectors laterally into a matrix.
For example, in a paper network, the paper nodes are identified as the numbers of the papers, the text content of the paper nodes is the title or abstract of the paper, the sequence length obtained by random walk is 5, and the walk isThe paper node identification sequence of the paper node is 1-3-6-4-9, the paper node content sequence is ' data-mining# ' - ' big data# ' - ' natural language processing ' - ' text analysis# ' - ' web data-mining ' - ' and# is a filling character, firstly, content words of each paper node are embedded and spliced, for example, words ' data ' are embedded to obtain 100-dimensional word vectors [1,0.89,1,23,0.54, …,1,03 ] corresponding to ' data ']The corresponding word vector is obtained for the content word of each paper node, and is spliced, such as the final result U (v) of the paper node content embedding with the node identification of 1 t ) Vectors of 3 x 100 dimensions [ [1,0.89,1,23,0.54, …,1,03 ]],[0.48,0.93,1.07,0.76,…,1.32],[1.78,1.24,0.65,0.79,…,0.36]]。
Using a plurality of widths k m Is set in U (v t ) Rolling and maximum pooling operations are performed on the model building machine, and the model building machine can model building
Figure SMS_16
Learning +.>
Figure SMS_17
Is>
Figure SMS_18
Figure SMS_19
Original thesis node content sequence
Figure SMS_20
Become the paper node semantic feature sequence +.>
Figure SMS_21
Figure SMS_22
T is the sequence length. After CNN modeling, for each paper node, the paper node content sequence embeds the result U (v t ) Convolving to a 100-dimensional vector ∈>
Figure SMS_23
Content feature vector of paper node as node identification 1 +.>
Figure SMS_24
Is [0.79,0.68,1.03,0.98, …,0.76]。
Step 2.2) the paper node content sequence coding of the paper node identification part:
node content sequence of paper
Figure SMS_25
In the method, semantic association information exists among different paper node contents, and in order to capture global semantic information existing in a paper node content sequence, a paper node semantic feature sequence output in a paper content embedding layer is +.>
Figure SMS_26
Above, bi-LSTM is used to encode the paper node semantic feature sequences. A forward LSTM will accumulate the semantic features of all paper nodes that the code is going to go through from the beginning of the sequence to get the current hidden state vector +.>
Figure SMS_27
/>
Figure SMS_28
The LSTM of the latter is used for accumulating the semantic features of all paper nodes from the end of the sequence to the current experience in the reverse order to obtain the current hidden state
Figure SMS_29
Figure SMS_30
wherein
Figure SMS_31
and />
Figure SMS_32
Respectively representing the fusion learning process performed by the forward and backward LSTM when processing the t-th paper node in the sequence.
The representation of the t-th paper node in the paper node content sequence encoding stage is as follows
Figure SMS_33
Figure SMS_34
For example, the paper node with node identification 1 is the first node in the sequence, so the corresponding forward hidden state is
Figure SMS_35
The corresponding backward hidden state is +>
Figure SMS_36
The paper node with final node identification of 1 is learned in the paper node content sequence coding stage as +.>
Figure SMS_37
and />
Figure SMS_38
Is->
Figure SMS_39
Is [0.38, -0.48, …,0.19,1.02, -0.98,1.29, …,0.96,1.20 ]]If the paper node with node identification 1 appears multiple times in the sequence, taking the average of the multiple paper node representations as the representation of the last paper node, and performing the same treatment when the paper node representations are calculated by other parts in the method.
Finally, the context characteristic representation of the whole paper node semantic characteristic sequence is obtained through splicing the final hidden state representation of the forward LSTM and the backward LSTM. Since the representation of the last hidden state of the forward and backward LSTM contains information of the entire sequence, the spliced last hidden state representation of the forward and backward LSTM is used as a representation of the entire sequence.
Figure SMS_40
Wherein [ · ]]Representing the process of longitudinally splicing vectors to finally obtain the contextual feature representation z of the whole paper node semantic feature sequence NI Is [1.39, -0.98, …,0.29,1.05]。
Step 2.3) paper node identification sequence generation of the paper node identification part:
the contextual characteristics obtained in step 2.2) represent z NI Fused paper node content sequence
Figure SMS_41
Content information of all paper nodes in +.>
Figure SMS_42
and />
Figure SMS_43
Sequence information carried by the user. To generate a corresponding paper node identification sequence, LSTM is first employed, in z NI As an initial state, a high-level implicit characteristic sequence oriented to the paper node identification space is directly generated without inputting the characteristic sequence>
Figure SMS_44
Wherein the t-th implicit feature->
Figure SMS_45
The generation process of (2) is as follows:
Figure SMS_46
then based on the high-layer implicit characteristic sequence obtained by decoding
Figure SMS_47
By means of full connectionThe junction layer adds each node feature in the high-level implicit feature sequence>
Figure SMS_48
Mapping to a node identification space to obtain the identification of the t-th paper node in the node identification space ∈>
Figure SMS_49
A semantic mapping from content modalities to structural modalities is achieved,
Figure SMS_50
wherein σ (·) is a sigmoid activation function, W NI-Tran and bNI-Tran The weight matrix and the bias term of the full connection layer are respectively. Subsequently, the softmax layer is further adopted
Figure SMS_51
Normalized to probability distribution over all |v| paper node identities:
Figure SMS_52
finally, probability distribution is obtained
Figure SMS_53
Is a probability value such as 0.29 #>
Figure SMS_54
The probability of j representing the predicted t-th paper node is 0.29. By comparing the probabilities on all |V| paper node identifiers, the paper node identifier with the highest probability value is finally taken as the predicted node identifier of the t-th paper node.
In the generation stage of the paper node identification sequence, the expression of the t-th paper node is as follows
Figure SMS_55
Figure SMS_56
The first paper node is represented as in the paper node identification sequence generation phase
Figure SMS_57
Figure SMS_58
Step 3) a paper node identification embedding for implementing a paper content generation part mapping from a paper node identification sequence to a paper node content sequence step 3.1) a paper content generation part
And adopting an paper node identification embedding layer, and obtaining vector representations of different paper nodes in the paper node identification sequence by looking up an initial embedding matrix of the paper nodes.
Figure SMS_59
wherein ,
Figure SMS_60
initializing an embedding matrix for all |v| paper node identities, | +.>
Figure SMS_61
Node identification vector, k, for the t-th paper node n Is the dimension of the embedded vector. Query function LookUp v (. Cndot.) identify each paper node +.>
Figure SMS_62
The corresponding embedded vector->
Figure SMS_63
Sequentially combined into sequence->
Figure SMS_64
For example, the random walk paper node identification sequence is 1- & gt 3- & gt 6- & gt 4- & gt 9, and the matrix V is embedded by searching, and each row of the matrix V represents the pairThe identification vector of the paper node at the position is used for obtaining k of each paper node n The identity vector of the dimension. The matrix v is initialized randomly, the identification vector of the paper node with the node identification of 1 is the first row in the matrix v, and the first row of the matrix v is taken as the paper node identification vector with the node identification of 1
Figure SMS_65
Step 3.2) encoding of the paper node identification sequence of the paper content Generation part
After obtaining
Figure SMS_66
Then, the Bi-LSTM is adopted to code the paper node identification sequence according to
Figure SMS_67
Sequence structure information between them, coding the paper node identification sequence into a context characteristic representation z CG As input to the subsequent content generation process. In the process->
Figure SMS_68
An embedded vector of each paper node identification +.>
Figure SMS_69
When a forward LSTM accumulates the identification features of all paper nodes from the beginning of the sequence to the current one, to obtain the current hidden state vector
Figure SMS_70
Figure SMS_71
Simultaneously, a backward LSTM is utilized to accumulate the identification characteristics of all paper nodes from the end of the sequence to the current experience in reverse order to obtain the current hidden state vector
Figure SMS_72
Figure SMS_73
wherein
Figure SMS_74
and />
Figure SMS_75
Respectively, the learning process performed by the forward and backward LSTM at step t.
The representation of the t-th paper node in the coding stage of the paper node identification sequence is as follows
Figure SMS_76
Figure SMS_77
For example, the paper node with node identification 1 is the first node in the sequence, so the corresponding forward hidden state is
Figure SMS_78
The corresponding backward hidden state is +>
Figure SMS_79
The paper node with final node identification of 1 is learned in the coding stage of the paper node identification sequence and is expressed as +.>
Figure SMS_80
and />
Figure SMS_81
Is->
Figure SMS_82
Is [0.32, -0.78, …,0.89,1.89, -0.38,1.02, …,0.39,1.01 ]].
By at least one of
Figure SMS_83
Iterative learning is performed, and structural semantic information in the paper node identification sequence is effectively mined from two opposite directions. And then, the final hidden state representation of the forward LSTM and the backward LSTM is spliced to obtain the fusion representation of the whole paper node identification sequence:
Figure SMS_84
wherein [ · ]]Representing the process of longitudinally splicing vectors to finally obtain the contextual feature representation z of the whole paper node identification feature sequence CG Is [1.39, -0.98, …,0.29,1.05]
Step 3.3) paper semantic decoding of paper content Generation part
After passing through the paper node identification embedding layer and the paper node identification sequence coding layer, the paper node identification sequence is already coded
Figure SMS_85
Fusing structural information in a compressed contextual feature representation z CG Is a kind of medium. As a key step before generating the paper node content, the contextual feature representation z is required CG Decoding to obtain semantic feature sequence of the whole paper sequence
Figure SMS_86
The method is used for connecting the two modal spaces of the network structure and the paper node content. Using LSTM, z is represented by contextual characteristics GG In the initial state, the output sequence is directly generated without inputting the characteristic sequence. Wherein semantic feature of the t-th paper node +.>
Figure SMS_87
The generation process of (2) is as follows: />
Figure SMS_88
Representing z based on contextual characteristics CG ，LSTM CG-Dec (. Cndot.) all T paper nodes are generated in sequence from front to backCorresponding content semantic features. Each of which is
Figure SMS_89
Has been fused with->
Figure SMS_90
The paper node identification information contained in the file and the sequence structure in the sequence are used as the basis for generating the content information. In addition, after the paper nodes in the input sequence are generated, the generation can be continued, and the semantic vectors of the new paper nodes can be predicted. Such as decoding +.>
Figure SMS_91
Can continue decoding +.>
Figure SMS_92
Content semantic vectors of new paper nodes are predicted.
In the thesis semantic decoding stage, the expression of the t-th thesis node is as follows
Figure SMS_93
Figure SMS_94
The first paper node is represented as in the paper semantic decoding stage
Figure SMS_95
Step 3.4) paper content Generation by the paper content Generation part
Finally, the sequence is characterized based on the paper semantics after decoding
Figure SMS_96
Each +.>
Figure SMS_97
Text content, i.e., word sequences, is generated. Following convention, LSTM is used to +.>
Figure SMS_98
As an initial state, word representation sequences of paper nodes are directly generated.
Given the maximum length L of the generated text, the LSTM will start from scratch, gradually generating a word sequence. When the length of the word sequence reaches L, or the generated word is the stop symbol < EOS >, the generation process stops. For the t-th paper node in the sequence, the implicit characterization of the first word is generated as follows:
Figure SMS_99
when l=1, the high-level semantic features are used
Figure SMS_101
To generate the 1 st hidden state directly without inputting features>
Figure SMS_103
For further generating words. And at l>1, the word vector of the last word which has been generated is characterized +.>
Figure SMS_105
As input feature, combine the transferred hidden state +.>
Figure SMS_102
Co-generation of the current hidden state->
Figure SMS_104
For further generation of the current word. In the training phase and the testing phase, the word vector characterization of the last word already generated ++>
Figure SMS_106
There are different arrangements. In the training process, in order to maximize likelihood probability of text content of paper node, from given +.>
Figure SMS_107
The first-1 real word is selected and its word vector is used as +.>
Figure SMS_100
The text content of the paper node with the node identification of 1 is input into the LSTM and is data mining#, and when the second word is predicted to be mining, an embedded vector [1,0.89,1,23,0.54, …,1,03 ] with the characteristic of data is input]：
Figure SMS_108
/>
And in the test phase, when predicting new text content for the paper node,
Figure SMS_109
the word vector corresponding to the word predicted in the previous step is:
Figure SMS_110
wherein
Figure SMS_111
Is about->
Figure SMS_112
The function of (2) represents the probability that the word predicted in the previous step is the jth word in the vocabulary, and the max function represents the word with the highest probability of generating the selection, for example, the maximum probability of the first word predicted for the paper node with node identification of 1 is "data", then the embedding vector of "data" is [1,0.89,1,23,0.54, …,1,03 ]]As input to predict the next word, i.e. +.>
Figure SMS_113
Based on the text generation process, a text semantic sequence with a length L (the maximum length of the word sequence of the paper node content is set to 3 in the example) is decoded for the t-th paper node in the sequence
Figure SMS_114
Using a fully-connected layer to connect each/>
Figure SMS_115
Mapping to +.>
Figure SMS_116
In the dictionary space of dimensions:
Figure SMS_117
wherein σ (·) is a sigmoid activation function, W CG-Word and bCG-Word Weight matrix and bias term of the full connection layer respectively, and adopt softmax layer to make
Figure SMS_118
Further conversion to at all->
Figure SMS_119
Probability distribution over individual words:
Figure SMS_120
finally, probability distribution is obtained
Figure SMS_121
Is a probability value such as 0.35, < >>
Figure SMS_122
The first word representing the node of the predictive t-th paper is m j The probability of (2) is 0.35. By comparison at all +.>
Figure SMS_123
And finally taking the word with the maximum probability value as the predicted word of the first word of the t-th node, and generating a result of data mining # for the content of the paper node with the node identification of 1.
For new decoded nodes if it is desired to predict the contents of the new paper node
Figure SMS_124
And executing the same content generation operation to generate a new content word sequence of the paper node.
Step 4) Dual fusion paper node identification part and paper content generation part
The paper node identification part and the paper content generation part are closely related, which model the cross-modal semantic generation relation between the paper node content sequence and the paper node identification sequence from two opposite angles, and in order to realize the fusion of complementary knowledge in two dual parts, the two parts are coupled together by using a linear layer and learning is performed simultaneously by using the sharing of an intermediate hidden layer.
Figure SMS_125
Figure SMS_126
wherein ,WDual,1 、b Dual,1 、W Dual,2 、b Dual,2 Is the weight and bias term of the linear fusion layer. After having undergone the above dual fusion process, at this time
Figure SMS_127
and />
Figure SMS_128
Some semantic information from the target modality has been included. Thus, will +.>
Figure SMS_129
and />
Figure SMS_130
And respectively feeding the decoding layers into the sequence decoding layers described in the step 2.3) and the step 3.3), thereby improving the accuracy of decoding and generating.
The vector of the final t-th paper node is expressed as:
Figure SMS_131
where [. Cndot. ] represents the process of stitching vectors longitudinally, such that the paper node with node identification 1 is ultimately represented as [0.38, -0.48, …,0.19,1.02, -0.98,1.29, …,0.96,1.20,0.37, -0.21, …,0.28,1.79,0.32, -0.78, …,0.89,1.89, -0.38,1.02, …,0.39,1.01,0.31, -0.51, …,0.78,1.23].

Claims (10)

1. The dual sequence-to-sequence generation-based paper network representation learning method is characterized by comprising the following steps of:
step 1) paper parallel sequence generation part
The random walk method is adopted to walk the paper network to obtain paper node sequences, and as each paper in the paper network has two types of information including paper numbers and paper text contents, each paper node sequence obtained by walk corresponds to two types of sequences including different information, namely a paper node identification sequence and a paper node content sequence, and the two types of sequences are a group of parallel sequences;
step 2) a paper node identification part for realizing mapping from a paper node content sequence to a paper node identification sequence
Step 2.1) embedding of paper content of the paper node identification part
For the text content of each paper node, firstly, segmenting the text, randomly initializing each word vector, then capturing the text content information of the paper node by adopting a convolutional neural network CNN, and obtaining the corresponding paper node semantic characteristics by each paper node;
step 2.2) encoding the content sequence of the paper node in the paper node identification section
The method comprises the steps of adopting a Bi-directional long-short-term memory network Bi-LSTM to encode a paper node content sequence, encoding the sequence into a context characteristic representation, adopting the Bi-LSTM to capture forward and reverse information of the paper sequence, and obtaining a semantic representation vector by encoding, wherein the semantic representation vector comprises semantic information of the whole paper node content sequence and structure information among paper nodes implied in the sequence, namely, quotation relations among papers;
step 2.3) generation of the paper node identification sequence of the paper node identification part
Decoding the semantic representation vector obtained by encoding through a long short-term memory network LSTM, and mapping the decoded vector into a paper node identification space to complete the generation process of a paper node identification sequence;
step 3) a paper content generation section for implementing mapping from a paper node identification sequence to a paper node content sequence
Step 3.1) paper node identification embedding in paper content Generation section
Adopting an paper node identification embedding layer, and obtaining vector representations of different paper node identifications in a paper node identification sequence by searching an initialization embedding matrix of the paper node;
step 3.2) encoding of the paper node identification sequence of the paper content Generation part
The method comprises the steps of adopting Bi-LSTM to encode an thesis node identification sequence, and encoding the thesis node identification sequence into a context characteristic representation according to sequence structure information among thesis nodes, namely, a quotation relation among papers, and taking the context characteristic representation as input of a subsequent semantic decoding process;
step 3.3) paper semantic decoding of paper content Generation part
Before the content of the paper node is generated, the context characteristic representation is required to be decoded to obtain a paper semantic characteristic sequence which is used for connecting two modal spaces of the paper network structure and the paper node content, and a decoder adopts LSTM;
step 3.4) paper content Generation by the paper content Generation part
Generating text content, namely word sequence, by adopting classical LSTM to semantic characterization of each paper node in the paper semantic feature sequence;
step 4) Dual fusion paper node identification part and paper content generation part
Through sharing of the intermediate hidden layers of the paper node identification part and the paper content generation part, the two parts are simultaneously learned, and the context characteristic representations obtained in the step 2.2) and the step 3.2) are fused in a linear fusion mode.
2. The method for learning the paper network representation based on dual sequence-to-sequence generation according to claim 1, wherein the method for generating the parallel sequence part of the paper in step 1) is as follows:
the paper network g= (V, E), V represents the set of all paper nodes in the network,
Figure FDA0004141174760000021
then it is a collection of edges in the paper network, V for each paper node V e V in the paper network i Representing the numbering of the nodes of the paper, using v c Content information representing paper nodes; the random walk method is adopted to walk the paper network, and a walk paper node sequence S= { v is obtained 1 ，v 2 ，...，v T T represents the number of nodes contained in the paper node sequence S, i.e. the sequence length, for each sequence S there is a corresponding paper node identification sequence +.>
Figure FDA0004141174760000022
And the thesis node content sequence->
Figure FDA0004141174760000023
The paper node identification sequence and the paper node content sequence are called a group of paper parallel sequences; paper node identification sequence
Figure FDA0004141174760000024
Containing structural information among paper nodes, namely quotation relation among papers, and the content sequence of the paper nodes
Figure FDA0004141174760000025
The content information and partial inter-paper structure information of the paper are contained, and because the two sequences contain different information, the paper network structure information can be fused through the mutual mapping process of the two sequencesInformation and paper node content information.
3. The method of claim 2, wherein the method of step 2.1) is as follows:
for the text content of each paper node, firstly, segmenting the text, randomly initializing each word vector, then capturing the text content information of the paper node by adopting CNN, and obtaining the corresponding node semantic feature by each paper node;
parallel sequences of articles are
Figure FDA0004141174760000026
wherein />
Figure FDA0004141174760000027
For the content sequence of the thesis node with the sequence length of T, < >>
Figure FDA0004141174760000028
The sequence is identified for the paper node with the sequence length of T, and the dictionary is +.>
Figure FDA0004141174760000029
Randomly initialized word embedding matrix is +.>
Figure FDA00041411747600000210
Figure FDA00041411747600000211
For the size of the dictionary, k m Representing the dimension of word embedding, first, a look-up function LookUp is adopted w (. Cndot. Cndot.) will be->
Figure FDA00041411747600000212
Text content of the t-th paper node in (2)>
Figure FDA0004141174760000031
Matrix formed by splicing word embedding vectors
Figure FDA0004141174760000032
wherein t＝1，2，...，T，u t，i For the i-th word in the node content of the t-th paper,>
Figure FDA0004141174760000033
number of content words for the t-th paper node:
Figure FDA0004141174760000034
wherein the operator is
Figure FDA0004141174760000035
Representing the operation of stitching the vectors laterally into a matrix;
using a plurality of widths k m Is set in U (v t ) Rolling and maximum pooling operations are performed on the model building machine, and modeling can be performed
Figure FDA0004141174760000036
Learning +.>
Figure FDA0004141174760000037
Is>
Figure FDA0004141174760000038
Figure FDA0004141174760000039
Original thesis node content sequence
Figure FDA00041411747600000310
Becoming a thesis node semantic feature sequence
Figure FDA00041411747600000311
T is the sequence length.
4. A method for learning a dual sequence-to-sequence generated paper web representation according to claim 3, wherein the method for encoding the paper node content sequence of the paper node identification part in step 2.2) is as follows:
node content sequence of paper
Figure FDA00041411747600000312
In the method, semantic association information exists among different paper node contents, and in order to capture global semantic information existing in a paper node content sequence, a paper node semantic feature sequence output by a paper content embedding method is +.>
Figure FDA00041411747600000313
The Bi-LSTM is adopted to code the semantic feature sequence of the paper node; a forward LSTM will accumulate the semantic features of all paper nodes that the code is going to go through from the beginning of the sequence to get the current hidden state vector +.>
Figure FDA00041411747600000314
Figure FDA00041411747600000315
The LSTM of the latter is used for accumulating the semantic features of all paper nodes from the end of the sequence to the current experience in the reverse order to obtain the current hidden state
Figure FDA00041411747600000316
Figure FDA00041411747600000317
wherein
Figure FDA00041411747600000318
and />
Figure FDA00041411747600000319
Representing forward and backward LSTM networks, respectively, < >>
Figure FDA00041411747600000320
And->
Figure FDA00041411747600000321
Respectively representing a forward hiding state and a backward hiding state corresponding to a T node, wherein the value range of T is t=1, 2;
the representation of the t-th paper node in the paper node content sequence encoding stage is as follows
Figure FDA0004141174760000041
Figure FDA0004141174760000042
Finally, the context feature representation z of the whole paper node semantic feature sequence is obtained by splicing the final hidden state representation of the forward LSTM and the backward LSTM NI ，
Figure FDA0004141174760000043
Where [. Cndot. ] represents the process of stitching vectors longitudinally.
5. The method for learning the network representation of the paper based on the dual sequence-to-sequence generation of claim 4, wherein the method for generating the sequence of the paper node identification part in the step 2.3) is as follows:
the contextual characteristics obtained in step 2.2) represent z NI Fused paper node content sequence
Figure FDA0004141174760000044
Content information of all paper nodes in +.>
Figure FDA0004141174760000045
and />
Figure FDA0004141174760000046
In order to generate corresponding paper node identification sequence, LSTM is adopted first to make z NI As an initial state, a high-level implicit characteristic sequence oriented to the paper node identification space is directly generated without inputting the characteristic sequence>
Figure FDA0004141174760000047
Wherein the t-th implicit feature->
Figure FDA0004141174760000048
The generation process of (2) is as follows:
Figure FDA0004141174760000049
then based on the high-layer implicit characteristic sequence obtained by decoding
Figure FDA00041411747600000410
Using the full connection layer to add each node feature in the high-level implicit feature sequence>
Figure FDA00041411747600000411
Is mapped to the node identification space,obtaining the identification of the t-th paper node in the node identification space ∈>
Figure FDA00041411747600000412
A semantic mapping from content modalities to structural modalities is achieved,
Figure FDA00041411747600000413
wherein σ (·) is a sigmoid activation function, W NI-Tran and bNm-Tran Respectively a weight matrix and a bias term of the full connection layer; subsequently, the softmax layer is further adopted
Figure FDA00041411747600000414
Normalized to the probability distribution over all |v| node identities:
Figure FDA00041411747600000415
in the generation stage of the paper node identification sequence, the expression of the t-th paper node is as follows
Figure FDA00041411747600000416
/>
Figure FDA00041411747600000417
6. The method for learning the dual sequence-to-sequence generated paper network representation according to claim 5, wherein the paper node identification embedding method of the paper content generating part in step 3.1) is as follows:
adopting a paper node identification embedding layer, and acquiring identification vector representations of different paper nodes in a paper node identification sequence by searching an initialization embedding matrix of the paper nodes;
Figure FDA0004141174760000051
wherein ,
Figure FDA0004141174760000052
initializing an embedding matrix for all |v| paper node identities, | +.>
Figure FDA0004141174760000053
Node identification vector, k, for the t-th paper node n Is the dimension of the embedded vector; query function LookUp v (. Cndot.). Cndot. Identifies each paper node
Figure FDA0004141174760000054
The corresponding embedded vector->
Figure FDA0004141174760000055
Sequentially combined into sequence->
Figure FDA0004141174760000056
7. The method for learning the network representation of the paper based on the dual sequence-to-sequence generation according to claim 6, wherein the method for encoding the node identification sequence of the paper in the paper content generation part in the step 3.2) is as follows:
after obtaining
Figure FDA0004141174760000057
Then, the Bi-LSTM is adopted to code the paper node identification sequence according to +.>
Figure FDA0004141174760000058
Sequence structure information between them, coding the paper node identification sequence into a context characteristic representation z CG As input to the subsequent paper content generation process; in the process->
Figure FDA0004141174760000059
An embedded vector of each paper node identification +.>
Figure FDA00041411747600000510
When a forward LSTM will accumulate the identification features of all paper nodes that the code goes through from the beginning of the sequence to the current, get the current hidden state vector +.>
Figure FDA00041411747600000511
Figure FDA00041411747600000512
Simultaneously, a backward LSTM is utilized to accumulate the identification characteristics of all paper nodes from the end of the sequence to the current experience in reverse order to obtain the current hidden state vector
Figure FDA00041411747600000513
Figure FDA00041411747600000514
wherein
Figure FDA00041411747600000515
and />
Figure FDA00041411747600000516
Representing forward and backward LSTM networks, respectively, < >>
Figure FDA00041411747600000517
And->
Figure FDA00041411747600000518
Respectively representing a forward hiding state and a backward hiding state corresponding to a T node, wherein the value range of T is t=1, 2;
the representation of the t-th paper node in the coding stage of the paper node identification sequence is as follows
Figure FDA00041411747600000519
Figure FDA00041411747600000520
By at least one of
Figure FDA00041411747600000521
And (3) performing iterative learning, namely effectively mining structural semantic information in the paper node identification sequence from two opposite directions, and then obtaining the representation of the whole paper node identification sequence by splicing the final hidden state representations of the forward LSTM and the backward LSTM:
Figure FDA0004141174760000061
8. the method for learning the dual sequence-to-sequence generated paper web representation according to claim 7, wherein the paper semantic decoding method of the paper content generating part in step 3.3) is as follows:
after passing through the paper node identification embedding layer and the paper node identification sequence coding layer, the paper node identification sequence is already coded
Figure FDA0004141174760000062
Fusing structural information in a compressed contextual feature representation z CG In this, as a key step before node content is generated, z needs to be represented for the context feature CG Decoding to obtain semantic feature sequence +.>
Figure FDA0004141174760000063
The system is used for connecting two modal spaces of a network structure and node contents; using LSTM, z is represented by contextual characteristics CG For initial state, directly generating output sequence without inputting feature sequence, wherein semantic feature of t-th paper node +.>
Figure FDA0004141174760000064
The generation process of (2) is as follows:
Figure FDA0004141174760000065
representing z based on contextual characteristics CG ，LSTM CG-Dec (. Cndot.) according to the sequence from front to back, sequentially generating content semantic features corresponding to all T paper nodes, each
Figure FDA0004141174760000066
Has been fused with->
Figure FDA0004141174760000067
The identity information of the paper nodes and the sequence structure in the sequence are used as the basis for generating content information; in addition, after the semantic vectors of the paper nodes in the input sequence are generated, the semantic vectors of new paper nodes can be continuously generated, and predicted;
in the thesis semantic decoding stage, the expression of the t-th thesis node is as follows
Figure FDA0004141174760000068
Figure FDA0004141174760000069
9. The method for learning the dual sequence-to-sequence generated paper web representation according to claim 8, wherein the paper content generating method in the paper content generating part in step 3.4) is as follows:
finally, based on the decoded paper semantic feature sequence
Figure FDA00041411747600000610
LSTM is adopted to->
Figure FDA00041411747600000611
As an initial state, directly generating a word representation sequence of the node;
given the maximum length L of the generated text, LSTM will start from scratch, gradually generating a word sequence, stopping the generation process when the length of the word sequence reaches L, or the generated word is stop sign < EOS >; for the t-th paper node in the sequence, the implicit characterization of the first word is generated as follows:
Figure FDA00041411747600000612
when l=1, the high-level semantic features are used
Figure FDA0004141174760000071
To be hidden, the 1 st hidden state is directly generated without inputting features
Figure FDA0004141174760000072
For further generating words; and when l > 1, the word vector of the last word which has been generated is characterized +.>
Figure FDA0004141174760000073
As input feature, combine the transferred hidden state +.>
Figure FDA0004141174760000074
Co-generation of the current hidden state->
Figure FDA0004141174760000075
For further generating a current word; in the training phase and the testing phase, the word vector characterization of the last word already generated ++>
Figure FDA0004141174760000076
There are different settings; in order to maximize the likelihood probability of the text content of the node during training, from a given +.>
Figure FDA0004141174760000077
The first-1 real word is selected and its word vector is used as +.>
Figure FDA0004141174760000078
Input into LSTM:
Figure FDA0004141174760000079
and in the test phase, when predicting new text content for the paper node,
Figure FDA00041411747600000710
the word vector corresponding to the word predicted in the previous step is:
Figure FDA00041411747600000711
wherein
Figure FDA00041411747600000712
Is about->
Figure FDA00041411747600000713
Representing the probability that the word predicted in the previous step is the jth word in the vocabulary, and selecting the word with the highest probability;
based on the text generation process, decoding text semantic sequence with length L for the t-th paper node in the sequence
Figure FDA00041411747600000714
Each +.>
Figure FDA00041411747600000715
Mapping to +.>
Figure FDA00041411747600000716
In the dictionary space of the dimension, the vector representation +.>
Figure FDA00041411747600000717
Figure FDA00041411747600000718
Wherein σ (·) is a sigmoid activation function, W GC-Word and bCG-Word Weight matrix and bias term of the full connection layer respectively, and adopt softmax layer to make
Figure FDA00041411747600000719
Further conversion to at all->
Figure FDA00041411747600000720
Probability distribution over individual words:
Figure FDA00041411747600000721
if the content of a new paper node is expected to be predicted, the same operation is performed on the semantic vector of the predicted new paper node, so that the content word sequence of the new paper node can be obtained.
10. The method for learning the network representation of the paper based on the dual sequence-to-sequence generation according to claim 9, wherein the method for the dual fusion paper node identification part and the paper content generation part in the step 4) is as follows:
the paper node identification part and the paper content generation part are closely related, which model the cross-modal semantic generation relation between the paper node content sequence and the paper node identification sequence from two opposite angles, and in order to realize the fusion of complementary knowledge in two dual parts, the two parts are coupled together by using a linear layer and learning is performed simultaneously by using the sharing of an intermediate hidden layer;
Figure FDA0004141174760000081
Figure FDA0004141174760000082
wherein ,WDual，1 、b Dual，1 、W Dual，2 、b Dual，2 The weight and bias term of the linear fusion layer; after having undergone the above dual fusion process, at this time
Figure FDA0004141174760000083
and />
Figure FDA0004141174760000084
Semantic information from the target modality has been included; thus, will +.>
Figure FDA0004141174760000085
Into the sequence decoding layers described in step 2.3) and step 3.3), respectively, to improve the accuracy of decoding and generation；
The vector of the final t-th paper node is expressed as:
Figure FDA0004141174760000086
/>
CN201911300281.1A 2019-12-17 2019-12-17 Dual-based sequence-to-sequence generation paper network representation learning method Active CN111104797B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911300281.1A CN111104797B (en) 2019-12-17 2019-12-17 Dual-based sequence-to-sequence generation paper network representation learning method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911300281.1A CN111104797B (en) 2019-12-17 2019-12-17 Dual-based sequence-to-sequence generation paper network representation learning method

Publications (2)

Publication Number Publication Date
CN111104797A CN111104797A (en) 2020-05-05
CN111104797B true CN111104797B (en) 2023-05-02

Family

ID=70423010

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911300281.1A Active CN111104797B (en) 2019-12-17 2019-12-17 Dual-based sequence-to-sequence generation paper network representation learning method

Country Status (1)

Country Link
CN (1) CN111104797B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111598223B (en) * 2020-05-15 2023-10-24 天津科技大学 Network embedding method based on attribute and structure depth fusion and model thereof
CN111708881A (en) * 2020-05-22 2020-09-25 国网天津市电力公司 Text representation learning method introducing incidence relation

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109558494A (en) * 2018-10-29 2019-04-02 中国科学院计算机网络信息中心 A kind of scholar's name disambiguation method based on heterogeneous network insertion
CN109710946A (en) * 2019-01-15 2019-05-03 福州大学 A kind of joint debate digging system and method based on dependence analytic tree
CN110008323A (en) * 2019-03-27 2019-07-12 北京百分点信息科技有限公司 A kind of the problem of semi-supervised learning combination integrated study, equivalence sentenced method for distinguishing

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109558494A (en) * 2018-10-29 2019-04-02 中国科学院计算机网络信息中心 A kind of scholar's name disambiguation method based on heterogeneous network insertion
CN109710946A (en) * 2019-01-15 2019-05-03 福州大学 A kind of joint debate digging system and method based on dependence analytic tree
CN110008323A (en) * 2019-03-27 2019-07-12 北京百分点信息科技有限公司 A kind of the problem of semi-supervised learning combination integrated study, equivalence sentenced method for distinguishing

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Na Li等.Hybrid algorithm based scheduling optimization in robotic cell with dual-gripper.《Proceeding of the IEEE International Conference on Information and Automation》.2014,第147-152页. *
Sindri Magn´usson等.Communication Complexity of Dual Decomposition Methods for Distributed Resource Allocation Optimization.《IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING》.2018,第第12卷卷(第第12卷期),第717-732页. *
江东灿 ; 陈维政 ; 闫宏飞 ; .基于deepwalk方法的适应有限文本信息的DWLTI算法.郑州大学学报(理学版).2017,49(01),第29-33页. *

Also Published As

Publication number Publication date
CN111104797A (en) 2020-05-05

Similar Documents

Publication Publication Date Title
CN111291212B (en) Zero sample sketch image retrieval method and system based on graph convolution neural network
CN109299342B (en) Cross-modal retrieval method based on cycle generation type countermeasure network
CN109492113B (en) Entity and relation combined extraction method for software defect knowledge
CN109299216A (en) A kind of cross-module state Hash search method and system merging supervision message
CN111538848A (en) Knowledge representation learning method fusing multi-source information
CN109101235A (en) A kind of intelligently parsing method of software program
CN111027595A (en) Double-stage semantic word vector generation method
CN111104797B (en) Dual-based sequence-to-sequence generation paper network representation learning method
CN113254616B (en) Intelligent question-answering system-oriented sentence vector generation method and system
CN112559764A (en) Content recommendation method based on domain knowledge graph
CN110781290A (en) Extraction method of structured text abstract of long chapter
CN113987169A (en) Text abstract generation method, device and equipment based on semantic block and storage medium
CN113971837A (en) Knowledge-based multi-modal feature fusion dynamic graph neural sign language translation method
Yi et al. Efficient online label consistent hashing for large-scale cross-modal retrieval
CN113300813A (en) Attention-based combined source channel method for text
Wang et al. Fusion-supervised deep cross-modal hashing
CN115510236A (en) Chapter-level event detection method based on information fusion and data enhancement
CN114281982B (en) Book propaganda abstract generation method and system adopting multi-mode fusion technology
CN117496388A (en) Cross-modal video description model based on dynamic memory network
CN111723649B (en) Short video event detection method based on semantic decomposition
CN117235216A (en) Knowledge reasoning method based on heterogeneous knowledge fusion
CN114298052B (en) Entity joint annotation relation extraction method and system based on probability graph
CN115730232A (en) Topic-correlation-based heterogeneous graph neural network cross-language text classification method
CN113254575B (en) Machine reading understanding method and system based on multi-step evidence reasoning
CN114358006A (en) Text content abstract generation method based on knowledge graph

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant