2020/09/28 by Fangyu Liu, Liu, Fangyu, Muhao Chen +5 · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Biomedical Text Mining and Ontologies #Computation and Language (cs.CL) #FOS: Computer and information sciences #Topic Modeling #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.2009.13603
To appear at AAAI-2021
openalex publication_date 2020/09/28 · arxiv created 2020/12/17 · arxiv updated 2020/12/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs). Images are natural components of many existing KGs. By combining visual knowledge with other auxiliary information, we show that the proposed new approach, EVA, creates a holistic entity representation that provides strong signals for cross-graph entity alignment. Besides, previous entity alignment methods require human labelled seed alignment, restricting availability. EVA provides a completely unsupervised solution by leveraging the visual similarity of entities to create an initial seed dictionary (visual pivots). Experiments on benchmark data sets DBP15k and DWY15k show that EVA offers state-of-the-art performance on both monolingual and cross-lingual entity alignment tasks. Furthermore, we discover that images are particularly useful to align long-tail KG entities, which inherently lack the structural contexts necessary for capturing the correspondences.