Generating Explanations To Understand And Repair Embedding-based Entity Alignment

Abstract

Entity alignment (EA) seeks identical entities in different knowledge graphs, which is a long-standing task in the database research. Recent work leverages deep learning to embed entities in vector space and align them via nearest neighbor search. Although embedding-based EA has gained marked success in recent years, it lacks explanations for alignment decisions. In this paper, we present the first framework that can generate explanations for understanding and repairing embedding-based EA results. Given an EA pair produced by an embedding model, we first compare its neighbor entities and relations to build a matching subgraph as a local explanation. We then construct an alignment dependency graph to understand the pair from an abstract perspective. Finally, we repair the pair by resolving three types of alignment conflicts based on dependency graphs. Experiments on a variety of EA datasets demonstrate the effectiveness, generalization, and robustness of our framework in explaining and

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keytian2023generating

Related papers

• Obtaining Example-based Explanations From Deep Neural Networks (2025)3.58
• Explore Entity Embedding Effectiveness In Entity Retrieval (2019)4.52
• Align Then Train: Efficient Retrieval Adapter Learning (2026)0.00
• Enterpriseem: Fine-tuned Embeddings For Enterprise Semantic Search (2024)0.00
• Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings (2022)11.85
• Deeper -- Deep Entity Resolution (2017)16.53
• PEARL: Prototype-enhanced Alignment For Label-efficient Representation Learning With Deployment-driven Insights From Digital Governance Communication Systems (2026)0.00
• HEAL: Hierarchical Embedding Alignment Loss For Improved Retrieval And Representation Learning (2024)2.26