What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings

TL;DR

This paper offers a theoretical perspective on entity alignment in multi-sourced knowledge graphs by framing it as a similarity flooding process, supported by experiments and new methods inspired by this view.

Contribution

It introduces a similarity flooding perspective to explain existing models and proposes two effective methods based on this theory for improved entity alignment.

Findings

Embedding learning seeks a fixpoint of pairwise similarities.

Proposed methods outperform baselines on benchmark datasets.

Theoretical analysis aligns with experimental results.

Abstract

Joint representation learning over multi-sourced knowledge graphs (KGs) yields transferable and expressive embeddings that improve downstream tasks. Entity alignment (EA) is a critical step in this process. Despite recent considerable research progress in embedding-based EA, how it works remains to be explored. In this paper, we provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models. We prove that the embedding learning process of these models actually seeks a fixpoint of pairwise similarities between entities. We also provide experimental evidence to support our theoretical analysis. We propose two simple but effective methods inspired by the fixpoint computation in similarity flooding, and demonstrate their effectiveness on benchmark datasets. Our work bridges the gap between recent embedding-based models and the conventional similarity flooding algorithm. It would improve our understanding of and increase our faith in embedding-based EA.