Interactive Contrastive Learning for Self-Supervised Entity Alignment
Kaisheng Zeng, Zhenhao Dong, Lei Hou, Yixin Cao, Minghao Hu, Jifan Yu, Xin Lv, Lei Cao, Xin Wang, Haozhuang Liu, Yi Huang, Junlan Feng, Jing Wan, Juanzi Li, Ling Feng
2022Proceedings of the 31st ACM International Conference on Information & Knowledge Management29 citationsDOIOpen Access PDF
Abstract
absolute improvement on average) and performs on par with previous SOTA supervised counterparts, demonstrating the effectiveness of the interactive contrastive learning for self-supervised EA. The code and data are available at https://github.com/THU-KEG/ICLEA.
Topics & Concepts
Computer scienceMargin (machine learning)Supervised learningArtificial intelligenceTask (project management)Natural language processingCode (set theory)Relation (database)Machine learningEncoderExploitData miningArtificial neural networkSet (abstract data type)ManagementProgramming languageEconomicsOperating systemComputer securityAdvanced Graph Neural NetworksTopic ModelingData Quality and Management