Interactive contrastive learning for self-supervised entity alignment

• Main Authors: ZENG, Kaisheng, DONG, Zhenhao, HOU, Lei, CAO, Yixin, HU, Minghao, YU, Jifan, LV, Xin, CAO, Lei, WANG, Xin, LIU, Haozhuang, HUANG, Yi, WAN, Jing, LI, Juanzi
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Knowledge Graph; Entity Alignment; Self-Supervised Learning; Contrastive Learning; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/7452; https://ink.library.smu.edu.sg/context/sis_research/article/8455/viewcontent/2201.06225.pdf
• Institution: Singapore Management University

Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without the use of pre-aligned entity pairs. The current state-of-the-art (SOTA) selfsupervised EA approach draws inspiration from contrastive learning, originally designed in computer visi...