🤖 AI Summary
Existing entity alignment methods for knowledge graphs suffer from high noise and low accuracy in pseudo-labeling, primarily due to neglecting the detrimental impact of alignment conflicts on iterative self-training.
Method: We propose the first Optimal Transport (OT)-based conflict-aware iterative pseudo-labeling framework. It enforces strict one-to-one matching constraints via OT to eliminate pseudo-label redundancy and conflicts. Additionally, we design a joint optimization mechanism integrating global–local aggregated GNN embeddings with explicit conflict modeling to dynamically identify and suppress erroneous alignment propagation.
Results: Our method achieves significant improvements over state-of-the-art approaches across multiple benchmark datasets—both with and without seed alignments—demonstrating strong generalizability. Notably, pseudo-label accuracy improves by up to 12.3%, validating the effectiveness of conflict-aware modeling and OT-driven pseudo-labeling.
📝 Abstract
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.
