Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignment
This addresses the challenge of integrating visual information for knowledge graph alignment, which is incremental as it builds on existing embedding methods by adding multi-modal features.
The paper tackled the problem of entity alignment in multi-modal knowledge graphs by constructing eight large-scale benchmarks with images and developing a new method combining logical deduction and embeddings, achieving state-of-the-art performance on these benchmarks.
Entity alignment (EA) for knowledge graphs (KGs) plays a critical role in knowledge engineering. Existing EA methods mostly focus on utilizing the graph structures and entity attributes (including literals), but ignore images that are common in modern multi-modal KGs. In this study we first constructed Multi-OpenEA -- eight large-scale, image-equipped EA benchmarks, and then evaluated some existing embedding-based methods for utilizing images. In view of the complementary nature of visual modal information and logical deduction, we further developed a new multi-modal EA method named LODEME using logical deduction and multi-modal KG embedding, with state-of-the-art performance achieved on Multi-OpenEA and other existing multi-modal EA benchmarks.