CN112487305A - GCN-based dynamic social user alignment method - Google Patents

GCN-based dynamic social user alignment method Download PDF

Info

Publication number
CN112487305A
CN112487305A CN202011388770.XA CN202011388770A CN112487305A CN 112487305 A CN112487305 A CN 112487305A CN 202011388770 A CN202011388770 A CN 202011388770A CN 112487305 A CN112487305 A CN 112487305A
Authority
CN
China
Prior art keywords
network
gcn
layer
nodes
matrix
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.)
Granted
Application number
CN202011388770.XA
Other languages
Chinese (zh)
Other versions
CN112487305B (en
Inventor
肖敏
何佳薇
刘立
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.)
Shenzhen Wanzhida Technology Transfer Center Co ltd
Original Assignee
Chongqing University of Post and Telecommunications
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 Chongqing University of Post and Telecommunications filed Critical Chongqing University of Post and Telecommunications
Priority to CN202011388770.XA priority Critical patent/CN112487305B/en
Publication of CN112487305A publication Critical patent/CN112487305A/en
Application granted granted Critical
Publication of CN112487305B publication Critical patent/CN112487305B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Abstract

The invention relates to a GCN-based dynamic social user alignment method, and belongs to the field of network analysis. Combining a fusion network Z by using the structures and the relations of the nodes and the edges in the source network and the target network, storing the structures of the nodes and the edges in the two networks, using the structures as initial input structures of the model, and generating a series of network snapshots Z according to the time sequence of the dynamic change of the network1，Z2，...ZT(ii) a And finally, outputting network representation through a full connection layer, defining a loss function at the full connection layer for node classification, and separating potential anchor nodes and non-anchor nodes. The invention can complete the user alignment task of the dynamic network under the deep neural network model, and hasMultidimensional information such as network structure information, attribute information, time information and the like is effectively stored, and the problems of retraining of a dynamic network user alignment task model, single training information and the like are solved.

Description

GCN-based dynamic social user alignment method
Technical Field
The invention belongs to the field of network analysis, and relates to a GCN-based dynamic social user alignment method.
Background
Each social platform reflects the interests of the user in different aspects, and the data can well help us to map the user roles in the virtual world into the real world. However, due to reasons related to user privacy protection and the like, data in different social platforms are often isolated from each other, and it is difficult to obtain complete information of a user in one social platform. Therefore, finding a connection between two social networks becomes an important issue, namely what we say social network user alignment. The purpose of user alignment is to find out the social network accounts belonging to the same person in different social networks. Currently, there have been many efforts in static social network user alignment for related research. However, researchers neglect the natural property of the dynamics of the network. The network is dynamically changed, and the evolution mode of the network dynamic change often contains abundant information. If the information can be used, the information is supposed to help people train better models.
Disclosure of Invention
In view of the above, the present invention provides a dynamic social user alignment method based on a GCN.
In order to achieve the purpose, the invention provides the following technical scheme:
a dynamic social user alignment method based on a graph neural network (GCN) comprises the following steps:
acquiring network structure information and tag information of anchor node users from a plurality of social networks, and fusing the network structure information and the tag information into a combined network according to rules of the combined network;
intercepting t according to time sequence when the social network platform changes at any time1To tnAnd constitute it into a combined network Z1To ZnAnd obtaining an adjacency matrix A of the combined network1，A2，...AT；
A is to be1Inputting a GCN layer to obtain a basic representation and a hidden state matrix of the whole network, and combining two t for capturing a dynamic network and improving the training efficiency of a modelnAnd tn-1The difference of the matrixes of the time is used as the input of the GCN layer;
laminating the GCN layer toTo hidden state matrix H1，ΔH2，...，ΔHnSequentially inputting the GRU layers, and obtaining a hidden state matrix h of the time information of the storage network through the GRU layersn；
Outputting a training result through a full-link layer, defining a loss function in the full-link layer to perform binary classification on the nodes, wherein the node with the classification result of 1 is a potential anchor node, and the node with the classification result of 0 is a non-anchor node;
the node classified as 1 in the combined network is a pair of potential anchor nodes in a source network and a target network, wherein the source network and the target network are network accounts belonging to the same person in reality.
Optionally, the merging of the combined networks into a combined network according to the rules of the combined network specifically includes:
setting the source network as X network, the target network as Y network, the combined network as Z network, GX，GY，GZRespectively, an undirected graph representing X, Y, Z a network; gX＝(VX,EX)，VXFor a set of nodes in network X, EXIs a set of edges in network X; gY＝(VY,EY)，VYFor a set of nodes in the network Y, EYIs the set of edges in network Y; gZ＝(VZ,EZ)，VZFor a set of nodes in the network Z, EZIs the set of edges in network Z;
Figure BDA0002810632930000021
representing nodes v in a combined networkiujRespectively by vi∈VX，uj∈VYComposition is carried out;
Figure BDA0002810632930000022
if (v)i,vk) And (u)j,ul) At GX，GYEdges are all present in the network, then edges (v) are present in the combined network Ziuj,vkul)。
Optionally, the operation formula of the GCN layer is as follows:
Figure BDA0002810632930000023
Hnis a hidden state matrix generated by the nth layer GCN,
Figure BDA0002810632930000024
is a regularized adjacency matrix that is a deformation of the adjacency matrix,
Figure BDA0002810632930000025
for the regularized band-from-loop adjacency matrix,
Figure BDA0002810632930000026
in order to have a self-looping abutment matrix,
Figure BDA0002810632930000027
for the degree of node i, W is the weight matrix trained by the GCN layer, and σ is the ReLU activation function.
Optionally, in the dynamic network, the network dynamically changes with time according to the time sequence T1,T2...TnDividing the network X and the network Y into n network snapshots respectively,
Figure BDA0002810632930000028
Figure BDA0002810632930000029
a combined network Z is generated from snapshots of network X and network Y,
Figure BDA00028106329300000210
deriving an adjacency matrix A of the combined network Z1,A2,...An(ii) a To capture dynamic network and improve model training efficiency, first, A1The input GCN layer obtains a basic representation of the whole network and combines two tnAnd tn-1Difference Δ A of the matrix of time instantsn＝An-An-1As an input to the GCN layer; the matrix input of the GCN layer is A1,ΔA2,ΔA 3...ΔAn。
Optionally, the GRU layer is used to represent time information of network dynamic change, and a formula of the GRU layer is as follows:
hn＝GRU(hn-1,Hn)
hnhidden state matrix output for the nth GRU, HnIs a hidden state matrix generated by the n-th layer GCN.
Optionally, the forward propagation formula of the GCN layer is as follows:
rt＝σ(Wrxt+Urht-1)
zt＝σ(Wzxt+Uzht-1)
Figure BDA00028106329300000211
Figure BDA00028106329300000212
rtreset gate for GRU, ztFor the update gate of GRU, W and U are both weight matrices, which are learned in training, xtFor input at the current time t, ht-1Is the hidden layer state at the moment of t-1, sigma is sigmoid function,
Figure BDA0002810632930000031
for resetting the hidden state of the gate calculation, htTo update the state update of the gate to the hidden,
Figure BDA0002810632930000032
for the hadamard product, corresponding elements in the operation matrix are multiplied.
Optionally, the nodes are classified by the full-connection layer, the node classified as 1 is a potential anchor node pair, the node classified as 0 is a non-anchor node, and a loss function defined in the full-connection layer is as follows:
Figure BDA0002810632930000033
f(hv) Function representing the entire depth model, yvThe labels are classified on behalf of the nodes.
The invention has the beneficial effects that: the invention completes the user alignment task of the dynamic network by constructing the deep neural network model, can effectively store multidimensional information such as network structure information, attribute information, time information and the like compared with the traditional model, can still obtain better accuracy under the condition of label information loss, can effectively solve the problems of retraining, single training information and the like of the dynamic network user alignment task model, and has certain improvement on the model efficiency.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a flowchart of a GCN-based dynamic social network user alignment method according to the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and examples may be combined with each other without conflict.
Wherein the showings are for the purpose of illustrating the invention only and not for the purpose of limiting the same, and in which there is shown by way of illustration only and not in the drawings in which there is no intention to limit the invention thereto; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", "front", "rear", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not an indication or suggestion that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes, and are not to be construed as limiting the present invention, and the specific meaning of the terms may be understood by those skilled in the art according to specific situations.
As shown in fig. 1, the present invention provides a method for dynamic social network user alignment of a GCN, which includes the following steps:
101. acquiring network structure information and tag information of anchor node users from a plurality of social networks, and fusing the network structure information and the tag information into a combined network according to rules of the combined network;
102. intercepting network snapshots t 1-tn according to a time sequence, forming a combined network Z1-Zn, and acquiring adjacency matrixes A1 and A2.. AT of the combined network;
103. inputting A1 and the difference between the two tn and tn-1 time matrixes into a GCN layer to obtain a basic representation and a hidden state matrix of the network;
104. inputting hidden state matrixes H1, delta H2.. delta Hn obtained by the GCN layer into the GRU layer in sequence, and obtaining a hidden state matrix for storing time information through the GRU layer;
105. and outputting the training result through the full-connection layer, and defining a loss function in the full-connection layer to perform binary classification on the nodes.
In step 101, the method includes obtaining a plurality of social network structure information and tag information of an anchor node user, and merging a combined network. Network alignment refers to finding social accounts belonging to the same person in multiple different social networks, and users with known identity attributes are referred to as anchor users. According to the invention, users in the social network platform are used as graph nodes, and a social network graph is constructed through social relations among networks. The two social networks are fused into one network to train the model, and the network alignment effect is obtained. The rule for merging two networks into a combined network is as follows:
setting the source network as X network, the target network as Y network, the combined network as Z network, GX，GY，GZRespectively, an undirected graph representing X, Y, Z a network. GX＝(VX,EX)，VXFor a set of nodes in network X, EXIs a set of edges in network X; gY＝(VY,EY)，VYFor a set of nodes in the network Y, EYIs the set of edges in network Y; gZ＝(VZ,EZ)，VZFor a set of nodes in the network Z, EZIs the set of edges in the network Z.
Figure BDA0002810632930000041
Representing nodes v in a combined networkiujRespectively by vi∈VX，uj∈VYComposition is carried out;
Figure BDA0002810632930000042
if (v)i,vk) And (u)j,ul) At GX，GYEdges are all present in the network, then edges (v) are present in the combined network Ziuj,vkul)。
In step 102, the network snapshot is intercepted in the time order t1 to tnAnd constructing a combined network Z1.. According to a time sequence T1,T2...TnThe network X and the network Y may be divided into n network snapshots respectively,
Figure BDA0002810632930000051
a combined network Z is generated from snapshots of network X and network Y,
Figure BDA0002810632930000052
deriving an adjacency matrix A of the combined network Z1,A2,...An. To capture the dynamic information of the network and improve the training efficiency of the model, first, A1The input GCN layer acquires a basic representation of the whole network, and then two tnAnd tn-1Difference Δ A of the matrix of time instantsn＝An-An-1As input to the GCN layer. The matrix input of the GCN layer is therefore A1,ΔA2,ΔA 3...ΔAn。
In step 103, the GCN layer represents the network structure information, and the operation formula of the GCN layer is as follows:
Figure BDA0002810632930000053
hn is the hidden state matrix generated by the nth layer GCN,
Figure BDA0002810632930000054
is a regularized adjacency matrix that is a deformation of the adjacency matrix,
Figure BDA0002810632930000055
for the regularized band-from-loop adjacency matrix,
Figure BDA0002810632930000056
in order to have a self-looping abutment matrix,
Figure BDA0002810632930000057
for the degree of node i, W is the weight matrix of GCN layer training, σ isThe ReLU activation function.
In step 104, the time information of the network dynamic change is represented by the GRU layer, and the formula of the GRU layer is as follows:
hn＝GRU(hn-1,Hn)
hn is a hidden state matrix output by the nth layer GRU, and Hn is a hidden state matrix generated by the nth layer GCN.
The forward propagation formula of the GCN layer is as follows:
rt＝σ(Wrxt+Urht-1)
zt＝σ(Wzxt+Uzht-1)
Figure BDA0002810632930000058
Figure BDA0002810632930000059
rtreset gate for GRU, ztFor the update gate of GRU, W and U are both weight matrices, which are learned in training, xtFor input at the current time t, ht-1Is the hidden layer state at the moment of t-1, sigma is sigmoid function,
Figure BDA00028106329300000510
for resetting the hidden state of the gate calculation, htTo update the state update of the gate to the hidden,
Figure BDA00028106329300000511
for the hadamard product, corresponding elements in the operation matrix are multiplied.
In step 105, the nodes are classified by the full link layer, the node classified as 1 is a potential anchor node pair, the node classified as 0 is a non-anchor node, and the loss function defined at the full link layer is as follows:
Figure BDA00028106329300000512
f(hv) Function representing the entire depth model, yvThe labels are classified on behalf of the nodes.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.

Claims (7)

1. A dynamic social user alignment method based on a graph neural network (GCN) is characterized in that: the method comprises the following steps:
acquiring network structure information and tag information of anchor node users from a plurality of social networks, and fusing the network structure information and the tag information into a combined network according to rules of the combined network;
intercepting t according to time sequence when the social network platform changes at any time1To tnAnd constitute it into a combined network Z1To ZnAnd obtaining an adjacency matrix A of the combined network1，A2，...AT；
A is to be1Inputting a GCN layer to obtain a basic representation and a hidden state matrix of the whole network, and combining two t for capturing a dynamic network and improving the training efficiency of a modelnAnd tn-1The difference of the matrixes of the time is used as the input of the GCN layer;
hidden state matrix H obtained by GCN layer1，ΔH2，...，ΔHnSequentially inputting the GRU layers, and obtaining a hidden state matrix h of the time information of the storage network through the GRU layersn；
Outputting a training result through a full-link layer, defining a loss function in the full-link layer to perform binary classification on the nodes, wherein the node with the classification result of 1 is a potential anchor node, and the node with the classification result of 0 is a non-anchor node;
the node classified as 1 in the combined network is a pair of potential anchor nodes in a source network and a target network, wherein the source network and the target network are network accounts belonging to the same person in reality.
2. The GCN-based dynamic social user alignment method of claim 1, wherein: the combination network which is fused into a combination network according to the rule of the combination network specifically comprises the following steps:
setting the source network as X network, the target network as Y network, the combined network as Z network, GX，GY，GZRespectively, an undirected graph representing X, Y, Z a network; gX＝(VX,EX)，VXFor a set of nodes in network X, EXIs a set of edges in network X; gY＝(VY,EY)，VYFor a set of nodes in the network Y, EYIs the set of edges in network Y; gZ＝(VZ,EZ)，VZFor a set of nodes in the network Z, EZIs the set of edges in network Z;
Figure FDA0002810632920000011
representing nodes v in a combined networkiujRespectively by vi∈VX，uj∈VYComposition is carried out;
Figure FDA0002810632920000012
if (v)i,vk) And (u)j,ul) At GX，GYEdges are all present in the network, then edges (v) are present in the combined network Ziuj,vkul)。
3. The GCN-based dynamic social user alignment method of claim 1, wherein: the operation formula of the GCN layer is as follows:
Figure FDA0002810632920000013
Hnis a hidden state matrix generated by the nth layer GCN,
Figure FDA0002810632920000014
is a regularized adjacency matrix that is a deformation of the adjacency matrix,
Figure FDA0002810632920000015
for the regularized band-from-loop adjacency matrix,
Figure FDA0002810632920000016
in order to have a self-looping abutment matrix,
Figure FDA0002810632920000017
for the degree of node i, W is the weight matrix trained by the GCN layer, and σ is the ReLU activation function.
4. The GCN-based dynamic social user alignment method of claim 1, wherein: in the dynamic network, the network changes dynamically with time according to a time sequence T1,T2...TnDividing the network X and the network Y into n network snapshots respectively,
Figure FDA0002810632920000021
a combined network Z is generated from snapshots of network X and network Y,
Figure FDA0002810632920000022
deriving an adjacency matrix A of the combined network Z1,A2,...An(ii) a To capture dynamic network and improve model training efficiency, first, A1The input GCN layer obtains a basic representation of the whole network and combines two tnAnd tn-1Difference Δ A of the matrix of time instantsn＝An-An-1As an input to the GCN layer; the matrix input of the GCN layer is A1,ΔA2,ΔA3...ΔAn。
5. The GCN-based dynamic social user alignment method of claim 1, wherein: and the GRU layer is used for representing the time information of the dynamic change of the network, and the formula of the GRU layer is as follows:
hn＝GRU(hn-1,Hn)
hnhidden state matrix output for the nth GRU, HnIs a hidden state matrix generated by the n-th layer GCN.
6. The GCN-based dynamic social user alignment method of claim 5, wherein: the forward propagation formula of the GCN layer is as follows:
rt＝σ(Wrxt+Urht-1)
zt＝σ(Wzxt+Uzht-1)
Figure FDA0002810632920000023
Figure FDA0002810632920000024
rtreset gate for GRU, ztFor the update gate of GRU, W and U are both weight matrices, which are learned in training, xtFor input at the current time t, ht-1Is the hidden layer state at the moment of t-1, sigma is sigmoid function,
Figure FDA0002810632920000025
for resetting the hidden state of the gate calculation, htTo update the state update of the gate to the hidden,
Figure FDA0002810632920000026
as Hadamard product, operating pairs in matrixMultiplication of corresponding elements.
7. The GCN-based dynamic social user alignment method of claim 1, wherein: classifying the nodes through the full connection layer, wherein the node classified as 1 is a potential anchor node pair, the node classified as 0 is a non-anchor node, and a loss function defined in the full connection layer is as follows:
Figure FDA0002810632920000027
f(hv) Function representing the entire depth model, yvThe labels are classified on behalf of the nodes.
CN202011388770.XA 2020-12-01 2020-12-01 GCN-based dynamic social user alignment method Active CN112487305B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011388770.XA CN112487305B (en) 2020-12-01 2020-12-01 GCN-based dynamic social user alignment method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011388770.XA CN112487305B (en) 2020-12-01 2020-12-01 GCN-based dynamic social user alignment method

Publications (2)

Publication Number Publication Date
CN112487305A true CN112487305A (en) 2021-03-12
CN112487305B CN112487305B (en) 2022-06-03

Family

ID=74938878

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011388770.XA Active CN112487305B (en) 2020-12-01 2020-12-01 GCN-based dynamic social user alignment method

Country Status (1)

Country Link
CN (1) CN112487305B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112953729A (en) * 2021-03-16 2021-06-11 讯翱（上海）科技有限公司 Digital certificate authentication method based on image recognition
CN113627591A (en) * 2021-07-30 2021-11-09 马上消费金融股份有限公司 Dynamic graph data processing method and device, electronic equipment and storage medium

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109062910A (en) * 2018-07-26 2018-12-21 苏州大学 Sentence alignment method based on deep neural network
CN109636658A (en) * 2019-01-17 2019-04-16 电子科技大学 A kind of social networks alignment schemes based on picture scroll product
US20190251480A1 (en) * 2018-02-09 2019-08-15 NEC Laboratories Europe GmbH Method and system for learning of classifier-independent node representations which carry class label information
CN110472065A (en) * 2019-07-25 2019-11-19 电子科技大学 Across linguistry map entity alignment schemes based on the twin network of GCN
WO2019219969A1 (en) * 2018-05-18 2019-11-21 Deepmind Technologies Limited Graph neural network systems for behavior prediction and reinforcement learning in multple agent environments
CN110929029A (en) * 2019-11-04 2020-03-27 中国科学院信息工程研究所 Text classification method and system based on graph convolution neural network
US20200125958A1 (en) * 2018-10-19 2020-04-23 Preferred Networks, Inc. Training apparatus, training method, inference apparatus, inference method, and non-transitory computer readable medium
CN111192154A (en) * 2019-12-25 2020-05-22 西安交通大学 Social network user node matching method based on style migration
CN111340112A (en) * 2020-02-26 2020-06-26 腾讯科技（深圳）有限公司 Classification method, classification device and server
CN111611785A (en) * 2020-04-30 2020-09-01 北京理工大学 Generation type confrontation network embedded representation learning method
CN111696345A (en) * 2020-05-08 2020-09-22 东南大学 Intelligent coupled large-scale data flow width learning rapid prediction algorithm based on network community detection and GCN
CN111723285A (en) * 2020-05-14 2020-09-29 天津大学 Depth spectrum convolution collaborative filtering recommendation method based on scores
EP3726525A1 (en) * 2017-12-14 2020-10-21 Samsung Electronics Co., Ltd. Electronic device for analyzing meaning of speech, and operation method therefor
CN111814066A (en) * 2020-07-01 2020-10-23 重庆邮电大学 Dynamic social user alignment method and system based on heuristic algorithm
CN112001185A (en) * 2020-08-26 2020-11-27 重庆理工大学 Emotion classification method combining Chinese syntax and graph convolution neural network

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3726525A1 (en) * 2017-12-14 2020-10-21 Samsung Electronics Co., Ltd. Electronic device for analyzing meaning of speech, and operation method therefor
US20190251480A1 (en) * 2018-02-09 2019-08-15 NEC Laboratories Europe GmbH Method and system for learning of classifier-independent node representations which carry class label information
WO2019219969A1 (en) * 2018-05-18 2019-11-21 Deepmind Technologies Limited Graph neural network systems for behavior prediction and reinforcement learning in multple agent environments
CN109062910A (en) * 2018-07-26 2018-12-21 苏州大学 Sentence alignment method based on deep neural network
US20200125958A1 (en) * 2018-10-19 2020-04-23 Preferred Networks, Inc. Training apparatus, training method, inference apparatus, inference method, and non-transitory computer readable medium
CN109636658A (en) * 2019-01-17 2019-04-16 电子科技大学 A kind of social networks alignment schemes based on picture scroll product
CN110472065A (en) * 2019-07-25 2019-11-19 电子科技大学 Across linguistry map entity alignment schemes based on the twin network of GCN
CN110929029A (en) * 2019-11-04 2020-03-27 中国科学院信息工程研究所 Text classification method and system based on graph convolution neural network
CN111192154A (en) * 2019-12-25 2020-05-22 西安交通大学 Social network user node matching method based on style migration
CN111340112A (en) * 2020-02-26 2020-06-26 腾讯科技（深圳）有限公司 Classification method, classification device and server
CN111611785A (en) * 2020-04-30 2020-09-01 北京理工大学 Generation type confrontation network embedded representation learning method
CN111696345A (en) * 2020-05-08 2020-09-22 东南大学 Intelligent coupled large-scale data flow width learning rapid prediction algorithm based on network community detection and GCN
CN111723285A (en) * 2020-05-14 2020-09-29 天津大学 Depth spectrum convolution collaborative filtering recommendation method based on scores
CN111814066A (en) * 2020-07-01 2020-10-23 重庆邮电大学 Dynamic social user alignment method and system based on heuristic algorithm
CN112001185A (en) * 2020-08-26 2020-11-27 重庆理工大学 Emotion classification method combining Chinese syntax and graph convolution neural network

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
HAO GAO等: "GCN-ALP: Addressing Matching Collisions in Anchor Link Prediction", 《 2020 IEEE INTERNATIONAL CONFERENCE ON KNOWLEDGE GRAPH (ICKG)》 *
HAO GAO等: "GCN-ALP: Addressing Matching Collisions in Anchor Link Prediction", 《 2020 IEEE INTERNATIONAL CONFERENCE ON KNOWLEDGE GRAPH (ICKG)》, 11 September 2020 (2020-09-11), pages 1 - 8 *
王晓浪等: "基于序列标注的事件联合抽取方法", 《重庆邮电大学学报(自然科学版)》 *
王晓浪等: "基于序列标注的事件联合抽取方法", 《重庆邮电大学学报(自然科学版)》, no. 05, 15 October 2020 (2020-10-15), pages 210 - 216 *
齐金山等: "大规模复杂信息网络表示学习:概念、方法与挑战", 《计算机学报》 *
齐金山等: "大规模复杂信息网络表示学习:概念、方法与挑战", 《计算机学报》, no. 10, 20 December 2017 (2017-12-20), pages 222 - 248 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112953729A (en) * 2021-03-16 2021-06-11 讯翱（上海）科技有限公司 Digital certificate authentication method based on image recognition
CN113627591A (en) * 2021-07-30 2021-11-09 马上消费金融股份有限公司 Dynamic graph data processing method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN112487305B (en) 2022-06-03

Similar Documents

Publication Publication Date Title
Lian et al. CCCFNet: A content-boosted collaborative filtering neural network for cross domain recommender systems
CN111428147B (en) Social recommendation method of heterogeneous graph volume network combining social and interest information
CN108920544A (en) A kind of personalized position recommended method of knowledge based map
CN110347932B (en) Cross-network user alignment method based on deep learning
CN111462282A (en) Scene graph generation method
CN114117220A (en) Deep reinforcement learning interactive recommendation system and method based on knowledge enhancement
CN110263236B (en) Social network user multi-label classification method based on dynamic multi-view learning model
CN112487305B (en) GCN-based dynamic social user alignment method
CN112200266B (en) Network training method and device based on graph structure data and node classification method
CN108062421A (en) A kind of extensive picture multiscale semanteme search method
CN112016601A (en) Network model construction method based on knowledge graph enhanced small sample visual classification
CN113407864B (en) Group recommendation method based on mixed attention network
CN104077279A (en) Parallel community discovery method and device
CN110502743A (en) Social networks based on confrontation study and semantic similarity is across media search method
CN112381179A (en) Heterogeneous graph classification method based on double-layer attention mechanism
CN104008177B (en) Rule base structure optimization and generation method and system towards linguistic indexing of pictures
CN112417289A (en) Information intelligent recommendation method based on deep clustering
CN115221413B (en) Sequence recommendation method and system based on interactive graph attention network
CN114065048A (en) Article recommendation method based on multi-different-pattern neural network
Huang et al. Prototype optimization for nearest-neighbor classification
Shen et al. RGBT tracking based on cooperative low-rank graph model
CN110111365B (en) Training method and device based on deep learning and target tracking method and device
CN116664719A (en) Image redrawing model training method, image redrawing method and device
CN115588122A (en) News classification method based on multi-mode feature fusion
CN108984551A (en) A kind of recommended method and system based on the multi-class soft cluster of joint

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
TR01 Transfer of patent right

Effective date of registration: 20240207

Address after: 1003, Building A, Zhiyun Industrial Park, No. 13 Huaxing Road, Henglang Community, Dalang Street, Longhua District, Shenzhen City, Guangdong Province, 518000

Patentee after: Shenzhen Wanzhida Technology Transfer Center Co.,Ltd.

Country or region after: China

Address before: 400065 Chongqing Nan'an District huangjuezhen pass Chongwen Road No. 2

Patentee before: CHONGQING University OF POSTS AND TELECOMMUNICATIONS

Country or region before: China

TR01 Transfer of patent right