{"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/ibmea-exploring-variational-information","title":"IBMEA: Exploring Variational Information Bottleneck for Multi-modal Entity Alignment","arxiv_id":"2407.19302","date":"2024-07-27","proceeding":null,"authors":["Taoyu Su","Jiawei Sheng","Shicheng Wang","Xinghua Zhang","Hongbo Xu","Tingwen Liu"],"abstract":"Multi-modal entity alignment (MMEA) aims to identify equivalent entities between multi-modal knowledge graphs (MMKGs), where the entities can be associated with related images. Most existing studies integrate multi-modal information heavily relying on the automatically-learned fusion module, rarely suppressing the redundant information for MMEA explicitly. To this end, we explore variational information bottleneck for multi-modal entity alignment (IBMEA), which emphasizes the alignment-relevant information and suppresses the alignment-irrelevant information in generating entity representations. Specifically, we devise multi-modal variational encoders to generate modal-specific entity representations as probability distributions. Then, we propose four modal-specific information bottleneck regularizers, limiting the misleading clues in refining modal-specific entity representations. Finally, we propose a modal-hybrid information contrastive regularizer to integrate all the refined modal-specific representations, enhancing the entity similarity between MMKGs to achieve MMEA. We conduct extensive experiments on two cross-KG and three bilingual MMEA datasets. Experimental results demonstrate that our model consistently outperforms previous state-of-the-art methods, and also shows promising and robust performance in low-resource and high-noise data scenarios.","url_abs":"https://arxiv.org/abs/2407.19302v1","url_pdf":"https://arxiv.org/pdf/2407.19302v1.pdf","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":"ibmea-exploring-variational-information","repo_url":"https://github.com/sutaoyu/IBMEA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"entity-alignment","task_name":"Entity Alignment"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"multi-modal-entity-alignment","task_name":"Multi-modal Entity Alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-modal-entity-alignment-on-mmkg","task":"Multi-modal Entity Alignment","dataset":"MMKG","model":"IBMEA","rank_in_archive_order":1,"of":1,"metrics":{"H@1":"0.631"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}