Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Conflict-Aware Pseudo Labeling via Optimal Transport for Entity Alignment

About

Entity alignment aims to discover unique equivalent entity pairs with the same meaning across different knowledge graphs (KGs). Existing models have focused on projecting KGs into a latent embedding space so that inherent semantics between entities can be captured for entity alignment. However, the adverse impacts of alignment conflicts have been largely overlooked during training, thereby limiting the entity alignment performance. To address this issue, we propose a novel Conflict-aware Pseudo Labeling via Optimal Transport model (CPL-OT) for entity alignment. The key idea is to iteratively pseudo-label alignment pairs empowered with conflict-aware optimal transport (OT) modeling to boost the precision of entity alignment. CPL-OT is composed of two key components -- entity embedding learning with global-local aggregation and iterative conflict-aware pseudo labeling -- that mutually reinforce each other. To mitigate alignment conflicts during pseudo labeling, we propose to use optimal transport as an effective means to warrant one-to-one entity alignment between two KGs with the minimal overall transport cost. Extensive experiments on benchmark datasets validate the superiority of CPL-OT over state-of-the-art baselines under both settings with and without prior alignment seeds.

Qijie Ding, Daokun Zhang, Jie Yin• 2022

Related benchmarks

TaskDatasetResultRank
Entity AlignmentDBP15K JA-EN (test)
Hits@195.6
149
Entity AlignmentDBP15K ZH-EN (test)
Hits@192.7
134
Entity AlignmentDBP15K FR-EN (test)
Hits@199
133
Entity AlignmentSPARS SRPRSEN_FR
Hit@197.4
6
Entity AlignmentSPARS SRPRSEN_DE
Hit@10.974
6
Showing 5 of 5 rows

Other info

Follow for update