mlsanityData to 14 Oct 2026

Cooperation of Experts: Fusing Heterogeneous Information with Large Margin

arXiv 2505.20853 ↗First posted 27 May 2025cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Fusing heterogeneous information remains a persistent challenge in modern data analysis. While significant progress has been made, existing approaches often fail to account for the inherent heterogeneity of object patterns across different semantic spaces. To address this limitation, we propose the Cooperation of Experts (CoE) framework, which encodes multi-typed information into unified heterogeneous multiplex networks. By overcoming modality and connection differences, CoE provides a powerful and flexible model for capturing the intricate structures of real-world complex data. In our framework, dedicated encoders act as domain-specific experts, each specializing in learning distinct relational patterns in specific semantic spaces. To enhance robustness and extract complementary knowledge, these experts collaborate through a novel large margin mechanism supported by a tailored optimization strategy. Rigorous theoretical analyses guarantee the framework's feasibility and stability, while extensive experiments across diverse benchmarks demonstrate its superior performance and broad applicability. Our code is available at https://github.com/strangeAlan/CoE.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 44 of its 60 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

44 of 60 references.

References · 44

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2019Simplifying Graph Convolutional Networkscited by 1,477
  4. 2019Heterogeneous Graph Attention Networkcited by 734
  5. 2019Graph Transformer Networkscited by 523
  6. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  7. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  8. 2019Learning Discrete Structures for Graph Neural Networkscited by 231
  9. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
  10. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
  11. 2020Learning Robust Representations via Multi-View Information Bottleneckcited by 191
  12. 2016On Deep Multi-View Representation Learning: Objectives and Optimizationcited by 162
32 more
  1. 2022Towards Unsupervised Deep Graph Structure Learningcited by 114
  2. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 110
  3. 2013From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviewscited by 108
  4. 2021HDMI: High-order Deep Multiplex Infomaxcited by 82
  5. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 82
  6. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  7. 2023Factorized Contrastive Learning: Going Beyond Multi-view Redundancycited by 75
  8. 2020Deep Partial Multi-View Learningcited by 71
  9. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 64
  10. 2019Graph-Revised Convolutional Networkcited by 59
  11. 2023GSLB: The Graph Structure Learning Benchmarkcited by 50
  12. 2024Reliable Conflictive Multi-View Learningcited by 45
  13. 2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
  14. 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clusteringcited by 29
  15. 2023PC-Conv: Unifying Homophily and Heterophily with Two-fold Filteringcited by 28
  16. 2022Multiplex Heterogeneous Graph Convolutional Networkcited by 27
  17. 2022Effects of Graph Convolutions in Multi-layer Networkscited by 24
  18. 2022Self-Supervised Graph Structure Refinement for Graph Neural Networkscited by 20
  19. 2019Relation Structure-Aware Heterogeneous Information Network Embeddingcited by 19
  20. 2024Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrastcited by 19
  21. 2022Learnware: Small Models Do Bigcited by 16
  22. 2023Adaptive Gating in Mixture-of-Experts based Language Modelscited by 16
  23. 2023Learning Topology-Specific Experts for Molecular Property Predictioncited by 15
  24. 2023Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clusteringcited by 12
  25. 2024When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learningcited by 12
  26. 2024Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learningcited by 12
  27. 2024Balanced Multi-Relational Graph Clusteringcited by 10
  28. 2024One Node One Model: Featuring the Missing-Half for Graph Clusteringcited by 7
  29. 2019Sequential Training of Neural Networks with Gradient Boostingcited by 6
  30. 2024A Margin-Maximizing Fine-Grained Ensemble Methodcited by 6
  31. 2024Mixture of Experts for Node Classificationcited by 4
  32. 2024GaGSL: Global-augmented Graph Structure Learning via Graph Information Bottleneckcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactionscited by 7
  2. 2026Structure-Centric Graph Foundation Model via Geometric Basescited by 5
  3. 2026Graph Domain Adaptation via Homophily-Agnostic Reconstructing Structurecited by 3
  4. 2026The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learningcited by 3
  5. 2025Hadamard-Riemannian Optimization for Margin-Variance Ensemblecited by 0
  6. 2025Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specializationcited by 0