{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/embedding-based-entity-alignment-using","title":"Embedding-Based Entity Alignment Using Relation Structural Similarity","arxiv_id":null,"date":"2022-09-11","proceeding":"2020 IEEE International Conference on Knowledge Graph (ICKG) 2022 9","authors":["Yanhui Peng; Jing Zhang; Cangqi Zhou; Jian Xu"],"abstract":"Entity alignment aims to find entities in different knowledge graphs that semantically represent the same real-world entity. Recently, embedding-based entity alignment methods, which represent knowledge graphs as low-dimensional embeddings and perform entity alignments by measuring the similarity between entity embeddings, have achieved promising results. Most of these methods mainly focus on improving the knowledge graph embedding model or leveraging attributes to obtain more semantic information. However, the structural similarity between the two relations (considering all entities attached on the two relations) in different KGs has not been utilized in the existing methods. In this paper, we propose a novel embedding-based entity alignment method that takes the advantages of relation structural similarity. Specifically, our method first jointly learns the embeddings of two knowledge graphs in a uniform vector space, using the entity pairs regarding to the seed alignments (the alignments already known) that each shares the same embedding. Then, it iteratively computes the structural similarity between the relations in different knowledge graphs according to the seed alignments and the alignments with high reliability generated during training, which makes the embeddings of relations with high similarity closer to each other. Experimental results on five widely used real-world datasets show that the proposed approach significantly outperforms the state-of-the-art embedding-based ones for entity alignment.","url_abs":"https://ieeexplore.ieee.org/document/9194492/authors","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9194492","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"embedding-based-entity-alignment-using","repo_url":"https://github.com/pengyanhui/RSimEA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"entity-alignment","task_name":"Entity Alignment"},{"task_slug":"entity-embeddings","task_name":"Entity Embeddings"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}