mlsanityData to 14 Oct 2026

MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid

arXiv 2212.14454 ↗First posted 29 Dec 2022cs.AI cs.CLcited by 30

Not on the map. Why?

Abstract (arXiv)

Multi-modal entity alignment (MMEA) aims to discover identical entities across different knowledge graphs (KGs) whose entities are associated with relevant images. However, current MMEA algorithms rely on KG-level modality fusion strategies for multi-modal entity representation, which ignores the variations of modality preferences of different entities, thus compromising robustness against noise in modalities such as blurry images and relations. This paper introduces MEAformer, a multi-modal entity alignment transformer approach for meta modality hybrid, which dynamically predicts the mutual correlation coefficients among modalities for more fine-grained entity-level modality fusion and alignment. Experimental results demonstrate that our model not only achieves SOTA performance in multiple training scenarios, including supervised, unsupervised, iterative, and low-resource settings, but also has a limited number of parameters, efficient runtime, and interpretability. Our code is available at https://github.com/zjukg/MEAformer.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 36 of its 69 references that are in the map. First posted on arXiv 29 Dec 2022.

Builds on

36 of 69 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  7. 2017Graph Attention Networkscited by 8,923
  8. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  9. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  10. 2021DeepViT: Towards Deeper Vision Transformercited by 289
  11. 2017Cross-lingual Entity Alignment via Joint Attribute-Preserving Embeddingcited by 127
  12. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trendscited by 117
24 more
  1. 2019Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphscited by 106
  2. 2019MMKG: Multi-Modal Knowledge Graphscited by 105
  3. 2019Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregationcited by 101
  4. 2019Multi-Channel Graph Neural Network for Entity Alignmentcited by 86
  5. 2019Multi-view Knowledge Graph Embedding for Entity Alignmentcited by 74
  6. 2019Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Networkcited by 68
  7. 2020Exploring and Evaluating Attributes, Values, and Structures for Entity Alignmentcited by 63
  8. 2021Molecular Contrastive Learning with Chemical Element Knowledge Graphcited by 50
  9. 2020Visual Pivoting for (Unsupervised) Entity Alignmentcited by 47
  10. 2019Aligning Cross-Lingual Entities with Multi-Aspect Informationcited by 46
  11. 2021OntoZSL: Ontology-enhanced Zero-shot Learningcited by 45
  12. 2020Neighborhood Matching Network for Entity Alignmentcited by 44
  13. 2020TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphscited by 41
  14. 2022Multi-modal Contrastive Representation Learning for Entity Alignmentcited by 38
  15. 2021Zero-shot Visual Question Answering using Knowledge Graphcited by 37
  16. 2021A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learningcited by 31
  17. 2019Collective Entity Alignment via Adaptive Featurescited by 30
  18. 2021From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignmentcited by 26
  19. 2020Relation-Aware Neighborhood Matching Model for Entity Alignmentcited by 20
  20. 2022ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similaritiescited by 20
  21. 2021OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embeddingcited by 19
  22. 2022LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injectioncited by 18
  23. 2022Informed Multi-context Entity Alignmentcited by 8
  24. 2022Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformercited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 11; 2024: 11; 2025: 4; 2026: 4.

30 papers.

Sort:

By area:

  1. 2023Large Language Models and Knowledge Graphs: Opportunities and Challengescited by 71
  2. 2023Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representationscited by 37
  3. 2023Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answeringcited by 29
  4. 2024NativE: Multi-modal Knowledge Graph Completion in the Wildcited by 23
  5. 2023Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignmentcited by 21
  6. 2024MKGL: Mastery of a Three-Word Languagecited by 17
  7. 2025PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignmentcited by 10
  8. 2024AVT2-DWF: Improving Deepfake Detection with Audio-Visual Fusion and Dynamic Weighting Strategiescited by 9
  9. 2023Revisit and Outstrip Entity Alignment: A Perspective of Generative Modelscited by 8
  10. 2024MCSFF: Multi-modal Consistency and Specificity Fusion Framework for Entity Alignmentcited by 8
  11. 2023Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignmentcited by 7
  12. 2024Pseudo-Label Calibration Semi-supervised Multi-Modal Entity Alignmentcited by 6
18 more
  1. 2024Progressively Modality Freezing for Multi-Modal Entity Alignmentcited by 5
  2. 2023Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classificationcited by 4
  3. 2023Retail-786k: a Large-Scale Dataset for Visual Entity Matchingcited by 2
  4. 2023Universal Multi-modal Entity Alignment via Iteratively Fusing Modality Similarity Pathscited by 2
  5. 2024Leveraging Intra-modal and Inter-modal Interaction for Multi-Modal Entity Alignmentcited by 2
  6. 2024LoginMEA: Local-to-Global Interaction Network for Multi-modal Entity Alignmentcited by 2
  7. 2024Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learningcited by 2
  8. 2024Multi-level Matching Network for Multimodal Entity Linkingcited by 2
  9. 2025K-ON: Stacking Knowledge On the Head Layer of Large Language Modelcited by 2
  10. 2025Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignmentcited by 2
  11. 2023MACO: A Modality Adversarial and Contrastive Framework for Modality-missing Multi-modal Knowledge Graph Completioncited by 1
  12. 2025Mitigating Modality Bias in Multi-modal Entity Alignment from a Causal Perspectivecited by 1
  13. 2023Type-enhanced Ensemble Triple Representation via Triple-aware Attention for Cross-lingual Entity Alignmentcited by 0
  14. 2024Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Textscited by 0
  15. 2026MyGram: Modality-aware Graph Transformer with Global Distribution for Multi-modal Entity Alignmentcited by 0
  16. 2026PSQE: A Theoretical-Practical Approach to Pseudo Seed Quality Enhancement for Unsupervised Multimodal Entity Alignmentcited by 0
  17. 2026Knowing When to Trust Images: Reliability-Aware Multi-modal Entity Alignmentcited by 0
  18. 2026Silence and Noise: Resolving Suppression and Overvaluation in Multimodal Entity Alignmentcited by 0