ML Anthology

Learning with Dual-Level Noisy Correspondence for Multi-Modal Entity Alignment

Haobin Li, Yijie Lin, Peng Hu, Mouxing Yang, Xi Peng
ICLR 2026
/iclr/2026/li2026iclr-learning-b/

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 DNC compared with seven state-of-the-art methods. Code is available at https://github.com/XLearning-SCU/2026-ICLR-RULE.

PDF ICLR OpenReview Semantic Scholar

Cite

Text

Li et al. "Learning with Dual-Level Noisy Correspondence for Multi-Modal Entity Alignment." International Conference on Learning Representations, 2026.

Markdown

[Li et al. "Learning with Dual-Level Noisy Correspondence for Multi-Modal Entity Alignment." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/li2026iclr-learning-b/)

BibTeX

@inproceedings{li2026iclr-learning-b,
  title     = {{Learning with Dual-Level Noisy Correspondence for Multi-Modal Entity Alignment}},
  author    = {Li, Haobin and Lin, Yijie and Hu, Peng and Yang, Mouxing and Peng, Xi},
  booktitle = {International Conference on Learning Representations},
  year      = {2026},
  url       = {https://mlanthology.org/iclr/2026/li2026iclr-learning-b/}
}