2 papers
cs.LG2024
TEA: Test-time Energy Adaptation
Yige Yuan, Bingbing Xu, Liang Hou +3
Test-time adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, offering the distinct advantage of not requiring access to tra…
cs.LG2024
Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets
Xuhui Jiang, Chengjin Xu, Yinghan Shen +7
The flourishing of knowledge graph applications has driven the need for entity alignment (EA) across KGs. However, the heterogeneity of practical KGs, characterized by differing sc…