# Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment

arXiv: https://arxiv.org/abs/2510.18240 · HTML: https://mlsanity.com/paper/2510.18240/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [MMKG: Multi-Modal Knowledge Graphs](https://mlsanity.com/paper/1903.05485/) (2019)
- [Multi-Modal Knowledge Graph Construction and Application: A Survey](https://mlsanity.com/paper/2202.05786/) (2022)
- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [Visual Pivoting for (Unsupervised) Entity Alignment](https://mlsanity.com/paper/2009.13603/) (2020)
- [Cross-Modality Perturbation Synergy Attack for Person Re-identification](https://mlsanity.com/paper/2401.10090/) (2024)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [Multi-modal Contrastive Representation Learning for Entity Alignment](https://mlsanity.com/paper/2209.00891/) (2022)
- [Enhance Vision-Language Alignment with Noise](https://mlsanity.com/paper/2412.10817/) (2024)
- [Graph Matching with Bi-level Noisy Correspondence](https://mlsanity.com/paper/2212.04085/) (2022)
- [MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid](https://mlsanity.com/paper/2212.14454/) (2022)
- [Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment](https://mlsanity.com/paper/2304.01563/) (2023)
- [Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment](https://mlsanity.com/paper/2307.16210/) (2023)
- [Multi-modal Entity Alignment in Hyperbolic Space](https://mlsanity.com/paper/2106.03619/) (2021)
- [Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets](https://mlsanity.com/paper/2304.03468/) (2023)
- [Progressively Modality Freezing for Multi-Modal Entity Alignment](https://mlsanity.com/paper/2407.16168/) (2024)
- [Dual Information Enhanced Multi-view Attributed Graph Clustering](https://mlsanity.com/paper/2211.14987/) (2022)

## Built on by (most cited first, 2 of 2)

- [Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2605.06083/) (2026)
- [Knowing When to Trust Images: Reliability-Aware Multi-modal Entity Alignment](https://mlsanity.com/paper/2609.23267/) (2026)

## Abstract (arXiv)

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 hrefhttps://github.com/XLearning-SCU/RULEXLearning-SCU/RULE