Research map / Vision-language and multimodal / Cross-modal learning
Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment
Haobin Li, Yijie Lin, Peng Hu, Mouxing Yang, Xi Peng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| apply RULE instead of best baseline, inherent noise, non-name attributes | RULE · ICEWS-WIKI Non-name | H@1: 53.5 -> 64.2 | Improved |
| apply RULE under 50% injected noise, non-name | RULE · Non-name avg over 5 datasets | Avg H@1: 54.0 -> 64.3 | Improved |
| apply RULE under 50% injected noise, all attributes | RULE · All-attributes avg over 5 datasets | Avg H@1: 94.7 -> 97.9 | Improved |
| increase injected noise from inherent to 50% (baselines degrade much more) | MEAformer · Non-name avg over 5 datasets | Avg H@1: 67.0 -> 54.0 | Hurt |
| increase injected noise from inherent to 50% for RULE | RULE · Non-name avg over 5 datasets | Avg H@1: 73.8 -> 64.3 | Hurt |
| add Dually Robust Learning (uncertainty or consensus) over plain MSE loss (ablation) | RULE · ICEWS-WIKI | H@1 | Improved |
| add test-time correspondence reasoning combining MLLM rethinking scores with prior similarity (ablation) | RULE · ICEWS-WIKI | H@1 | Improved |
| add Dually Robust Fusion module (ablation) | RULE · ICEWS-WIKI | H@1 | Improved |
Closest papers by meaning
- Tackling Uncertain Correspondences for Multi-Modal Entity Alignment (NeurIPS 2024 · similarity 0.92)
- Pseudo-Label Calibration Semi-supervised Multi-Modal Entity Alignment (AAAI 2024 · similarity 0.90)
- Entity Alignment with Noisy Annotations from Large Language Models (NeurIPS 2024 · similarity 0.88)
- HLMEA: Unsupervised Entity Alignment Based on Hybrid Language Models (AAAI 2025 · similarity 0.88)
- NeuSymEA: Neuro-symbolic Entity Alignment via Variational Inference (NeurIPS 2025 · similarity 0.87)
- MESED: A Multi-Modal Entity Set Expansion Dataset with Fine-Grained Semantic Classes and Hard Negative Entities (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
