{"ID":2852006,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.18240","arxiv_id":"2510.18240","title":"Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment","abstract":"Multi-modal entity alignment (MMEA) aims to identify equivalent entities across heterogeneous multi-modal knowledge graphs (MMKGs), where each entity is described by attributes from various modalities. Existing methods typically assume that both intra-entity and inter-graph correspondences are faultless, which is often violated in real-world MMKGs due to the reliance on expert annotations. In this paper, we reveal and study a highly practical yet under-explored problem in MMEA, termed Dual-level Noisy Correspondence (DNC). DNC refers to misalignments in both intra-entity (entity-attribute) and inter-graph (entity-entity and attribute-attribute) correspondences. To address the DNC problem, we propose a robust MMEA framework termed RULE. RULE first estimates the reliability of both intra-entity and inter-graph correspondences via a dedicated two-fold principle. Leveraging the estimated reliabilities, RULE mitigates the negative impact of intra-entity noise during attribute fusion and prevents overfitting to noisy inter-graph correspondences during inter-graph discrepancy elimination. Beyond the training-time designs, RULE further incorporates a correspondence reasoning module that uncovers the underlying attribute-attribute connection across graphs, guaranteeing more accurate equivalent entity identification. Extensive experiments on five benchmarks verify the effectiveness of our method against the DNC compared with seven state-of-the-art methods.The code is available at \\href{https://github.com/XLearning-SCU/RULE}{XLearning-SCU/RULE}","short_abstract":"Multi-modal entity alignment (MMEA) aims to identify equivalent entities across heterogeneous multi-modal knowledge graphs (MMKGs), where each entity is described by attributes from various modalities. Existing methods typically assume that both intra-entity and inter-graph correspondences are faultless, which is often...","url_abs":"https://arxiv.org/abs/2510.18240","url_pdf":"https://arxiv.org/pdf/2510.18240v1","authors":"[\"Haobin Li\",\"Yijie Lin\",\"Peng Hu\",\"Mouxing Yang\",\"Xi Peng\"]","published":"2025-10-21T03:00:11Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":607951,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2852006,"paper_url":"https://arxiv.org/abs/2510.18240","paper_title":"Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment","repo_url":"https://github.com/XLearning-SCU/RULE","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}