mlsanityData to 14 Oct 2026

Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning

arXiv 2409.17386 ↗First posted 25 Sep 2024cs.LG cs.AI cs.SIcited by 12

Not on the map. Why?

Abstract (arXiv)

Unsupervised Multiplex Graph Learning (UMGL) aims to learn node representations on various edge types without manual labeling. However, existing research overlooks a key factor: the reliability of the graph structure. Real-world data often exhibit a complex nature and contain abundant task-irrelevant noise, severely compromising UMGL's performance. Moreover, existing methods primarily rely on contrastive learning to maximize mutual information across different graphs, limiting them to multiplex graph redundant scenarios and failing to capture view-unique task-relevant information. In this paper, we focus on a more realistic and challenging task: to unsupervisedly learn a fused graph from multiple graphs that preserve sufficient task-relevant information while removing task-irrelevant noise. Specifically, our proposed Information-aware Unsupervised Multiplex Graph Fusion framework (InfoMGF) uses graph structure refinement to eliminate irrelevant noise and simultaneously maximizes view-shared and view-unique task-relevant information, thereby tackling the frontier of non-redundant multiplex graph. Theoretical analyses further guarantee the effectiveness of InfoMGF. Comprehensive experiments against various baselines on different downstream tasks demonstrate its superior performance and robustness. Surprisingly, our unsupervised method even beats the sophisticated supervised approaches. The source code and datasets are available at https://github.com/zxlearningdeep/InfoMGF.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 53 of its 70 references that are in the map. First posted on arXiv 25 Sep 2024.

Builds on

53 of 70 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  5. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  6. 2019Simplifying Graph Convolutional Networkscited by 1,477
  7. 2016Variational Graph Auto-Encoderscited by 1,382
  8. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  9. 2018Deep Graph Infomaxcited by 1,106
  10. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  11. 2019Heterogeneous Graph Attention Networkcited by 734
  12. 2020Self-supervised Learning: Generative or Contrastivecited by 694
38 more
  1. 2020A Survey on Contrastive Self-supervised Learningcited by 554
  2. 2019Graph Transformer Networkscited by 523
  3. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 429
  4. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  5. 2021Graph Self-Supervised Learning: A Surveycited by 289
  6. 2019Learning Discrete Structures for Graph Neural Networkscited by 231
  7. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 215
  8. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
  9. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
  10. 2020Data Augmentation for Graph Neural Networkscited by 203
  11. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  12. 2020Learning Robust Representations via Multi-View Information Bottleneckcited by 191
  13. 2020Contrastive learning, multi-view redundancy, and linear modelscited by 146
  14. 2022Towards Unsupervised Deep Graph Structure Learningcited by 114
  15. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 110
  16. 2019Unsupervised Attributed Multiplex Network Embeddingcited by 95
  17. 2021HDMI: High-order Deep Multiplex Infomaxcited by 82
  18. 2022What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoderscited by 82
  19. 2021Multi-view Contrastive Graph Clusteringcited by 76
  20. 2023Factorized Contrastive Learning: Going Beyond Multi-view Redundancycited by 75
  21. 2022Rethinking Minimal Sufficient Representation in Contrastive Learningcited by 69
  22. 2022A Survey on Graph Representation Learning Methodscited by 66
  23. 2019Graph-Revised Convolutional Networkcited by 59
  24. 2023GSLB: The Graph Structure Learning Benchmarkcited by 50
  25. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  26. 2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
  27. 2017An Attention-based Collaboration Framework for Multi-View Network Representation Learningcited by 31
  28. 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clusteringcited by 29
  29. 2023PC-Conv: Unifying Homophily and Heterophily with Two-fold Filteringcited by 28
  30. 2022Effects of Graph Convolutions in Multi-layer Networkscited by 24
  31. 2023Data-centric Graph Learning: A Surveycited by 22
  32. 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
  33. 2022Self-Supervised Graph Structure Refinement for Graph Neural Networkscited by 20
  34. 2019Relation Structure-Aware Heterogeneous Information Network Embeddingcited by 19
  35. 2020Mutual Information Gradient Estimation for Representation Learningcited by 14
  36. 2023Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clusteringcited by 12
  37. 2024Balanced Multi-Relational Graph Clusteringcited by 10
  38. 2021Multilayer Graph Contrastive Clustering Networkcited by 8

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 7.

12 papers.

  1. 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 42
  2. 2025Cooperation of Experts: Fusing Heterogeneous Information with Large Margincited by 6
  3. 2026Structure-Centric Graph Foundation Model via Geometric Basescited by 5
  4. 2026Graph Domain Adaptation via Homophily-Agnostic Reconstructing Structurecited by 3
  5. 2025Fine-grained Spatio-temporal Event Prediction with Self-adaptive Anchor Graphcited by 2
  6. 2025Effective Clustering for Large Multi-Relational Graphscited by 2
  7. 2026Mapping Text to Multiplex Graph: Prompt Compression as L'evy Walk-Guided Graph Pruningcited by 1
  8. 2025DRKF: Decoupled Representations with Knowledge Fusion for Multimodal Emotion Recognitioncited by 0
  9. 2026Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classificationcited by 0
  10. 2026Informative Graph Structure Learningcited by 0
  11. 2026FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defensecited by 0
  12. 2026Preserving Geometric Integrity in Graph Prompting via Measure-Constrained Optimal Transportcited by 0