mlsanityData to 14 Oct 2026

Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering

arXiv 2305.02931 ↗First posted 3 May 2023cs.SI cs.AI cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) based methods have achieved impressive performance on node clustering task. However, they are designed on the homophilic assumption of graph and clustering on heterophilic graph is overlooked. Due to the lack of labels, it is impossible to first identify a graph as homophilic or heterophilic before a suitable GNN model can be found. Hence, clustering on real-world graph with various levels of homophily poses a new challenge to the graph research community. To fill this gap, we propose a novel graph clustering method, which contains three key components: graph reconstruction, a mixed filter, and dual graph clustering network. To be graph-agnostic, we empirically construct two graphs which are high homophily and heterophily from each data. The mixed filter based on the new graphs extracts both low-frequency and high-frequency information. To reduce the adverse coupling between node attribute and topological structure, we separately map them into two subspaces in dual graph clustering network. Extensive experiments on 11 benchmark graphs demonstrate our promising performance. In particular, our method dominates others on heterophilic graphs.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 3 May 2023.

Builds on

35 of 47 references.

References · 35

  1. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  2. 2016Variational Graph Auto-Encoderscited by 1,382
  3. 2020Simple and Deep Graph Convolutional Networkscited by 860
  4. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  5. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  6. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  7. 2019Multi-scale Attributed Node Embeddingcited by 548
  8. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  9. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
  10. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  11. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  12. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
23 more
  1. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  2. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  3. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  4. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  5. 2019Attributed Graph Clustering: A Deep Attentional Embedding Approachcited by 149
  6. 2020Structural Deep Clustering Networkcited by 145
  7. 2021Deep Graph Clustering via Dual Correlation Reductioncited by 97
  8. 2019Attributed Graph Clustering via Adaptive Graph Convolutioncited by 96
  9. 2020Adaptive Graph Encoder for Attributed Graph Embeddingcited by 89
  10. 2019Learning Graph Embedding with Adversarial Training Methodscited by 84
  11. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  12. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
  13. 2021Multi-view Contrastive Graph Clusteringcited by 76
  14. 2020Deep Fusion Clustering Networkcited by 71
  15. 2021Attention-driven Graph Clustering Networkcited by 40
  16. 2021Rethinking Graph Auto-Encoder Models for Attributed Graph Clusteringcited by 37
  17. 2021Tree Decomposed Graph Neural Networkcited by 35
  18. 2022Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approachcited by 23
  19. 2022Structure-Preserving Graph Representation Learningcited by 17
  20. 2022Graph Soft-Contrastive Learning via Neighborhood Rankingcited by 16
  21. 2021Self-supervised Consensus Representation Learning for Attributed Graphcited by 15
  22. 2019RWR-GAE: Random Walk Regularization for Graph Auto Encoderscited by 10
  23. 2021Multilayer Graph Contrastive Clustering Networkcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 11; 2025: 8; 2026: 6.

29 papers.

Sort:

  1. 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 42
  2. 2023PC-Conv: Unifying Homophily and Heterophily with Two-fold Filteringcited by 28
  3. 2023Efficient Heterogeneous Graph Learning via Random Projectioncited by 16
  4. 2024CDC: A Simple Framework for Complex Data Clusteringcited by 15
  5. 2023Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clusteringcited by 12
  6. 2024When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learningcited by 12
  7. 2024Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learningcited by 12
  8. 2023Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfercited by 10
  9. 2024Balanced Multi-Relational Graph Clusteringcited by 10
  10. 2025Cooperation of Experts: Fusing Heterogeneous Information with Large Margincited by 6
  11. 2024Provable Filter for Real-world Graph Clusteringcited by 5
  12. 2026Structure-Centric Graph Foundation Model via Geometric Basescited by 5
17 more
  1. 2025Learning Laplacian Positional Encodings for Heterophilous Graphscited by 4
  2. 2024Simplified PCNet with Robustnesscited by 3
  3. 2025Adaptive Homophily Clustering: Structure Homophily Graph Learning with Adaptive Filter for Hyperspectral Imagecited by 3
  4. 2026Graph Domain Adaptation via Homophily-Agnostic Reconstructing Structurecited by 3
  5. 2024Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness-Generalization Perspectivecited by 2
  6. 2025ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusioncited by 2
  7. 2025Effective Clustering for Large Multi-Relational Graphscited by 2
  8. 2024Topology Reorganized Graph Contrastive Learning with Mitigating Semantic Driftcited by 1
  9. 2026Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clusteringcited by 1
  10. 2024HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learningcited by 0
  11. 2024Probability Passing for Graph Neural Networks: Graph Structure and Representations Joint Learningcited by 0
  12. 2024Boolean Product Graph Neural Networkscited by 0
  13. 2025Aggregation-aware MLP: An Unsupervised Approach for Graph Message-passingcited by 0
  14. 2025Attention Beyond Neighborhoods: Reviving Transformer for Graph Clusteringcited by 0
  15. 2026Weighted Graph Clustering via Scale Contraction and Graph Structure Learningcited by 0
  16. 2026Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classificationcited by 0
  17. 2026Unsupervised Graph Representation Learning with Complementary View Alignmentcited by 0