基于霍克斯过程的动态异质网络表征学习方法

陈蕾; 邓琨; 刘星妍

doi:10.11959/j.issn.1000-0801.2024195

您当前的位置：

首页 >

文章列表页 >

基于霍克斯过程的动态异质网络表征学习方法

研究与开发 | 更新时间：2024-09-23

- 基于霍克斯过程的动态异质网络表征学习方法
- Dynamic heterogeneous network representation learning method based on Hawkes process
- 电信科学 2024年40卷第8期页码：78-93
- 作者机构：
  
  1.嘉兴大学信息科学与工程学院，浙江嘉兴 314001
  2.浙江师范大学计算机科学与技术学院（人工智能学院），浙江金华 321004
  3.嘉兴大学浙江省医学电子与数字健康重点实验室，浙江嘉兴 314001
- 作者简介：
  
  [ "陈蕾（2000- ），女，浙江师范大学计算机科学与技术学院（人工智能学院）硕士生，主要研究方向为社会网络分析和异质网络表征学习。" ]
  [ "邓琨（1980- ），男，博士，嘉兴大学信息科学与工程学院、嘉兴大学浙江省医学电子与数字健康重点实验室副教授、硕士生导师，主要研究方向为网络结构分析、数据挖掘、异质网络分析等。" ]
  [ "刘星妍（1980- ），女，嘉兴大学信息科学与工程学院高级工程师，主要研究方向为数据挖掘、网络结构分析等。" ]
- 基金信息：
  
  教育部人文社会科学研究专项任务项目(22JDSZ3023);教育部产学合作协同育人项目(220603372015422;220604029012441)
- DOI：10.11959/j.issn.1000-0801.2024195
  中图分类号： TP391
- 收稿：2024-04-02，
  
  修回：2024-08-05，
  
  纸质出版：2024-08-20
- 稿件说明：
移动端阅览
陈蕾,邓琨,刘星妍.基于霍克斯过程的动态异质网络表征学习方法[J].电信科学,2024,40(08):78-93.

CHEN Lei,DENG Kun,LIU Xingyan.Dynamic heterogeneous network representation learning method based on Hawkes process[J].Telecommunications Science,2024,40(08):78-93.
陈蕾,邓琨,刘星妍.基于霍克斯过程的动态异质网络表征学习方法[J].电信科学,2024,40(08):78-93. DOI： 10.11959/j.issn.1000-0801.2024195.

CHEN Lei,DENG Kun,LIU Xingyan.Dynamic heterogeneous network representation learning method based on Hawkes process[J].Telecommunications Science,2024,40(08):78-93. DOI： 10.11959/j.issn.1000-0801.2024195.

摘要

现有的异质网络表征学习方法主要关注静态网络，忽略了时间属性对节点表示的重要影响。然而，真实的异质信息网络极具动态性，节点和边的微小变化都可能影响整个结构和语义。鉴于此，提出了基于霍克斯过程的动态异质网络表征学习方法。首先，利用关系旋转编码方式和注意力机制，学习相邻节点的注意力系数，获得节点的向量表示。其次，学习不同元路径的最优加权组合以更好捕获网络的结构和语义信息。最后，基于时间衰减效应，通过邻域形成序列将时间特征引入节点表示中，得到节点的最终嵌入表示。在多种基准数据集上的实验结果表明，所提方法在性能上显著优于对比模型。在节点分类任务中，Macro-F1平均提高了0.15%～3.45%，在节点聚类任务中，归一化互信息（normalized mutual information，NMI）值提高了1.08%～3.57%。

Abstract

Existing methods for heterogeneous network representation learning mainly focus on static networks

overlooking the significant impact of temporal attributes on node representations. However

real heterogeneous information networks are very dynamic

and even minor changes in nodes and edges can affect the entire structure and semantics. In this context

a dynamic heterogeneous network representation learning method based on Hawkes process was proposed. Firstly

the vector representation of nodes was obtained by utilizing the relational rotation encoding method and attention mechanism

where the attention coefficients of adjacent nodes were learned. Secondly

the optimal weighted combination of different meta-paths was learned to better captures the structural and semantic information of the network. Finally

leveraging the time decay effect

time features were introduced into node representations through the formation of neighborhood sequences

resulting in the ultimate embedding representation of nodes. Experimental results on various benchmark datasets indicate that the proposed method significantly outperforms baseline methods. In node classification tasks

Macro-F1 average is increased by 0.15% to 3.45%

and NMI value in node clustering tasks is improved by 1.08% to 3.57%.

关键词

Keywords

references

DAI S J , YU Y W , FAN H , et al . Spatio-temporal representation learning with social tie for personalized POI recommendation [J ] . Data Science and Engineering , 2022 , 7 ( 1 ): 44 - 56 .

杨帅 , 王瑞琴 , 马辉 . 基于多通道的边学习图卷积网络 [J ] . 电信科学 , 2022 , 38 ( 9 ): 95 - 104 .

YANG S , WANG R Q , MA H . Multi-channel based edge-learning graph convolutional network [J ] . Telecommunications Science , 2022 , 38 ( 9 ): 95 - 104 .

CHANG L , MA C , SUN K , et al . Enhanced road information representation in graph recurrent network for traffic speed prediction [J ] . IET Intelligent Transport Systems , 2023 , 17 ( 7 ): 1434 - 1453 .

HE L , GUO W Z , CHEN Y Z , et al . Discovering overlapping communities in dynamic networks based on cascade information diffusion [J ] . IEEE Transactions on Computational Social Systems , 2022 , 9 ( 3 ): 794 - 806 .

SONG R , GIUNCHIGLIA F , ZHAO K , et al . Topological enhanced graph neural networks for semi-supervised node classification [J ] . Applied Intelligence , 2023 , 53 ( 20 ): 23538 - 23552 .

WANG W , SUO X Y , WEI X Y , et al . HGATE: heterogeneous graph attention auto-encoders [J ] . IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 4 ): 3938 - 3951 .

WANG X , JI H Y , SHI C , et al . Heterogeneous graph attention network [C ] // Proceedings of the World Wide Web Conference . New York : ACM , 2019 : 2022 - 2032 .

YANG C , LIU Z Y , ZHAO D L , et al . Network representation learning with rich text information [C ] // Proceedings of the 24th International Conference on Artificial Intelligence . Menlo Park : AAAI Press , 2015 : 2111 - 2117 .

SHI C , HU B B , ZHAO W X , et al . Heterogeneous information network embedding for recommendation [J ] . IEEE Transactions on Knowledge and Data Engineering , 2019 , 31 ( 2 ): 357 - 370 .

ZHU D Y , CUI P , ZHANG Z W , et al . High-order proximity preserved embedding for dynamic networks [J ] . IEEE Transactions on Knowledge and Data Engineering , 2018 , 30 ( 11 ): 2134 - 2144 .

NGUYEN G H , LEE J B , ROSSI R A , et al . Continuous-time dynamic network embeddings [C ] // Proceedings of the Companion of the The Web Conference 2018 . New York : ACM Press , 2018 : 969 - 976 .

LU Y F , WANG X , SHI C , et al . Temporal network embedding with micro- and macro-dynamics [C ] // Proceedings of the Proceedings of the 28th ACM International Conference on Information and Knowledge Management . New York : ACM Press , 2019 : 469 - 478 .

LI X , DING D H , KAO B , et al . Leveraging meta-path contexts for classification in heterogeneous information networks [C ] // Proceedings of the 2021 IEEE 37th International Conference on Data Engineering (ICDE) . Piscataway : IEEE Press , 2021 : 912 - 923 .

YANG Y M , GUAN Z Y , LI J X , et al . Interpretable and efficient heterogeneous graph convolutional network [J ] . IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 2 ): 1637 - 1650 .

贾霄生 , 赵中英 , 李超 , 等 . 互信息与多条元路径融合的异质网络表示学习方法 [J ] . 软件学报 , 2023 , 34 ( 7 ): 3256 - 3271 .

JIA X S , ZHAO Z Y , LI C , et al . Heterogeneous network representation learning method fusing mutual information and multiple meta-paths [J ] . Journal of Software , 2023 , 34 ( 7 ): 3256 - 3271 .

ZHOU L K , YANG Y , REN X , et al . Dynamic network embedding by modeling triadic closure process [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2018 , 32 ( 1 ): 571 - 578 .

ZUO Y , LIU G N , LIN H , et al . Embedding temporal network via neighborhood formation [C ] // Proceedings of the Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . New York : ACM , 2018 : 2857 - 2866 .

尹赢 , 张建朋 , 吉立新 , 等 . 基于霍克斯点过程的动态网络表示学习方法 [J ] . 电子学报 , 2020 , 48 ( 11 ): 2154 - 2161 .

YIN Y , ZHANG J P , JI L X , et al . Dynamic network representation learning based on hawkes point process [J ] . Acta Electronica Sinica , 2020 , 48 ( 11 ): 2154 - 2161 .

XUE H S , YANG L W , JIANG W , et al . Modeling dynamic heterogeneous network for link prediction using hierarchical attention with temporal RNN [C ] //HUTTER F, KERSTING K, LIJFFIJT J, et al. Joint European Conference on Machine Learning and Knowledge Discovery in Databases . Cham : Springer , 2021 : 282 - 298 .

WANG X , LU Y F , SHI C , et al . Dynamic heterogeneous information network embedding with meta-path based proximity [J ] . IEEE Transactions on Knowledge and Data Engineering , 2022 , 34 ( 3 ): 1117 - 1132 .

FAN Y J , JU M X , ZHANG C X , et al . Heterogeneous temporal graph neural network [M ] // Proceedings of the 2022 SIAM International Conference on Data Mining (SDM) . Philadelphia, PA : Society for Industrial and Applied Mathematics , 2022 : 657 - 665 .

郭佳雯 , 白淇介 , 林铸天 , 等 . 基于非递减时序随机游走的动态异质网络嵌入 [J ] . 计算机研究与发展 , 2021 , 58 ( 8 ): 1624 - 1641 .

GUO J W , BAI Q J , LIN Z T , et al . Dynamic heterogeneous network embedding based on non-decreasing temporal random walk [J ] . Journal of Computer Research and Development , 2021 , 58 ( 8 ): 1624 - 1641 .

秦海盈 , 赵中英 , 李建晖 , 等 . 基于元路径与层次注意力的时序异质信息网络表示学习方法 [J ] . 模式识别与人工智能 , 2021 , 34 ( 12 ): 1093 - 1102 .

QIN H Y , ZHAO Z Y , LI J H , et al . Meta-path and hierarchical attention based temporal heterogeneous information network representation learning [J ] . Pattern Recognition and Artificial Intelligence , 2021 , 34 ( 12 ): 1093 - 1102 .

刘群 , 谭洪胜 , 张优敏 , 等 . 基于元路径的动态异质网络表示学习 [J ] . 电子学报 , 2022 , 50 ( 8 ): 1830 - 1839 .

LIU Q , TAN H S , ZHANG Y M , et al . Dynamic heterogeneous network representation method based on meta-path [J ] . Acta Electronica Sinica , 2022 , 50 ( 8 ): 1830 - 1839 .

LIANG X X , MA Y , CHENG G Q , et al . Meta-path-based heterogeneous graph neural networks in academic network [J ] . International Journal of Machine Learning and Cybernetics , 2022 , 13 ( 6 ): 1553 - 1569 .

FU X Y , ZHANG J N , MENG Z Q , et al . MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding [C ] // Proceedings of the Proceedings of The Web Conference 2020 . New York : ACM , 2020 : 2331 - 2341 .

SUN Z Q , DENG Z H , NIE J Y , et al . RotatE: knowledge graph embedding by relational rotation in complex space [J ] . arXiv preprint , arXiv: 1902.10197 , 2019 .

VELICKOVIC P , CUCURULL G , CASANOVA A , et al . Graph attention networks [J ] . arXiv preprint , arXiv: 1710.10903 , 2017 .

WU N , WANG C F . Heterogeneous graph tree networks [J ] . arXiv preprint , arXiv: 2209.00610 , 2022 .

YANG X C , YAN M Y , PAN S R , et al . Simple and efficient heterogeneous graph neural network [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 9 ): 10816 - 10824 .

YAN Y Y , LI C , YU Y W , et al . OSGNN: original graph and Subgraph aggregated Graph Neural Network [J ] . Expert Systems with Applications , 2023 , 225 : 120115 .

浏览量

618

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于移动通信网信号的人体动作识别研究

基于拓扑信息增强的异构图神经网络算法

基于多通道超图卷积与跨视图对比学习的会话推荐

基于GNN与注意力机制的文本分类模型

基于多尺度残差时间卷积网络的物联网入侵检测模型