| 108 | 1 | 7 |
| 下载次数 | 被引频次 | 阅读次数 |
针对异质网络表示学习中邻接节点表示向量的融合问题，提出基于多臂老虎机的异质网络表示学习方法。该方法采用基于多臂老虎机思想，实现异质网络中元路径关系的权重的自适应计算，在节点分类任务上取得的Micro-F1值（89.56%和54.79%）和Macro-F1值（89.09%和53.14%）均优于基准测试。面对节点信息的多样性，基于多臂老虎机的网络表示学习方法能够将网络结构和节点信息更加有效地融入图的表示学习中。
Abstract：To deal with the fusion of adjacent node representation vectors in heterogeneous network representation learning, an adaptive calculation of relationship weights of meta-path relations in heterogeneous networks is achieved by adopting the idea of multi-armed bandit. By introducing the above measures, this method achieved Micro-F1 values of89.56% and 54.79%, as well as Macro-F1 values of 89.09% and 53.14% in node classification tasks. The research results show that in the face of the diversity of node information, the network representation learning method based on multi-armed bandit can more effectively integrate network structure and node information into graph representation learning.
[1] WANG Y W,WANG W,LIANG Y X,et al. NodeAug:semi-supervised node classification with data augmentation[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery&Data Mining. Virtual Event,CA,USA. ACM,2020:207-217.
[2] KUMAR A,SINGH S S,SINGH K,et al. Link prediction techniques,applications,and performance:a survey[J]. Physica A Statistical Mechanics and Its Applications,2020,553:124289.
[3] WU S,SUN F,ZHANG W,et al. Graph neural networks in recommender systems:a survey[J]. ACM Computing Surveys,2022,55(5):1-37.
[4] XIAO M,QIAO Z Y,FU Y J,et al. Hierarchical interdisciplinary topic detection model for research proposal classification[J]. IEEE Transactions on Knowledge and Data Engineering,2023,35(9):9685-9699.
[5] ROSSETTI G,CAZABET R. Community discovery in dynamicnetworks:asurvey[J].ACMComputingSurveys,51(2):35.
[6] GROVER A,LESKOVEC J. Node2vec:scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA:ACM,2016:855-864.
[7] 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. New York USA:ACM,2014:701-710.
[8]涂存超，杨成，刘知远，等.网络表示学习综述[J].中国科学（信息科学），2017,47(8):980-996.
[9] CAO S S,LU W,XU Q K. GraRep:learning graph representations with global structural information[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. Melbourne,Australia:ACM,2015:891-900.
[10]WANG D X,CUI P,ZHU W W. Structural deep network embedding[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco,California,USA:ACM,2016:1225-1234.
[11]ROWEIS S T,SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science,2000,290:2323-2326.
[12] BORDES A,USUNIER N,GARCIA-DURAN A,et al. Translating embeddings for modeling multi-relational data[C]//BOTTOU L,Proc. of Neural Information Processing Systems.La Jolla:Neural Information Processing System. New York:Association for Computing Machinery,2013,26.
[13]DETTMERS T,MINERVINI P,STENETORP P,et al. Convolutional 2D knowledge graph embeddings[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2018,32(1):18-36.
[14]FU T Y,LEE W C,LEI Z. HIN2Vec:explore meta-paths in heterogeneous information networks for representation learning[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. Singapore,Singapore:ACM,2017:1797-1806.
[15] DONG Y X,CHAWLA N V,SWAMI A. Metapath2vec:scalable representation learning for heterogeneous networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Halifax,NS,Canada:ACM,2017:135-144.
[16] SCHLICHTKRULL M,KIPF T,BLOEM P,et al. Modeling relationaldata with graph convolutional networks[C]/RUDOLPH S,Proc. of the 15th Extended Semantic Web Conference. New York:Springer,2018:593-607.
[17] LU Y F,SHI C,HU L M,et al. Relation structure-aware heterogeneous information network embedding[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2019,33(1):4456-4463.
[18] WU F,SOUZA A,ZHANG T,et al. Simplifying graph convolutional networks[C]//MOHAMED S,Proc. of International Conference on Machine Learning. Cambridge:MIT Press,2019:6861-6871.
[19]VELIKOVI P,CUCURULL G,CASANOVA A,et al. Bengio Y,Graph Attention Networks[C]//PINEAU J,Proc. of International Conference on Learning Representations. Cambridge:MIT Press,2018:1223-1233.
[20]WANG X,JI H Y,SHI C,et al. Heterogeneous graph attention network[C]//The World Wide Web Conference. San Francisco CA USA:ACM,2019:2022-2032.
基本信息:
DOI：10.19573/j.issn2095-0926.202401011
中图分类号:O157.5
引用信息:
[1]闫旸,陈泽秋,邓钧霖.基于多臂老虎机的异质网络表示学习方法[J].天津职业技术师范大学学报,2024,34(01):61-65.DOI:10.19573/j.issn2095-0926.202401011.
基金信息:
教育部人文社会科学研究规划基金青年基金项目（22YJC870018）; 天津市教委科研计划项目（2020KJ112）; 应用数学福建省高校重点实验室开放课题（SX201904）; 天津职业技术师范大学人才启动项目（KYQD1817）