mlsanityData to 7 Oct 2026

Graph Neural Networks for Graphs with Heterophily: A Survey

arXiv 2202.07082 ↗First posted 14 Feb 2022cs.LGcited by 175

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriad graph analytic tasks and applications. Most GNNs rely on the homophily assumption that nodes belonging to the same class are more likely to be connected. However, as a ubiquitous graph property in numerous real-world scenarios, heterophily, i.e., nodes with different labels tend to be linked, significantly limits the performance of tailor-made homophilic GNNs. Hence, GNNs for heterophilic graphs are gaining increasing research attention to enhance graph learning with heterophily. In this paper, we provide a comprehensive review of GNNs for heterophilic graphs. Specifically, we propose a systematic taxonomy that governs existing heterophilic GNN models, along with general summaries and detailed analyses. Furthermore, we discuss the relationship between heterophily and various graph research domains, aiming to facilitate the development of more effective GNNs across a spectrum of practical applications and learning tasks in the graph research community. In the end, we point out potential directions to advance and inspire future research and applications on heterophilic graph learning with GNNs.

Key facts. Cited by 175 papers in the map (data through 7 Oct 2026). Builds on 58 of its 168 references that are in the map. First posted on arXiv 14 Feb 2022.

Builds on

58 of 168 references.

References · 58

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  9. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  10. 2020Simple and Deep Graph Convolutional Networkscited by 857
  11. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  12. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
38 more
  1. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  2. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  3. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  4. 2019Multi-scale Attributed Node Embeddingcited by 543
  5. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  6. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  7. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  8. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  9. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  10. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  11. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  12. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 208
  13. 2020Graph Neural Networks with Heterophilycited by 202
  14. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  15. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  16. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  17. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  18. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  19. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  20. 2022Towards Unsupervised Deep Graph Structure Learningcited by 112
  21. 2019Learning Disentangled Representations for Recommendationcited by 110
  22. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  23. 2020Non-Local Graph Neural Networkscited by 91
  24. 2021GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophilycited by 84
  25. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  26. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
  27. 2020Graph Geometry Interaction Learningcited by 55
  28. 2020PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecastingcited by 52
  29. 2021Generative hypergraph clustering: from blockmodels to modularitycited by 48
  30. 2021Tree Decomposed Graph Neural Networkcited by 35
  31. 2021Block Modeling-Guided Graph Convolutional Neural Networkscited by 32
  32. 2019Clustering in graphs and hypergraphs with categorical edge labelscited by 31
  33. 2021Graph Pointer Neural Networkscited by 27
  34. 2015Homophily and missing links in citation networkscited by 21
  35. 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
  36. 2021Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspectivecited by 19
  37. 2021Label-Wise Graph Convolutional Network for Heterophilic Graphscited by 17
  38. 2022Simplified Graph Convolution with Heterophilycited by 17

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 18; 2023: 38; 2024: 57; 2025: 40; 2026: 22.

175 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  2. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  3. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  4. 2022Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminationcited by 67
  5. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 46
  6. 2023Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detectioncited by 43
  7. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  8. 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 41
  9. 2024Deep Graph Anomaly Detection: A Survey and New Perspectivescited by 40
  10. 2023Simple and Asymmetric Graph Contrastive Learning without Augmentationscited by 37
  11. 2023Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoderscited by 32
  12. 2024The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challengescited by 29
38 more
  1. 2022A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resourcecited by 26
  2. 2023Learning Strong Graph Neural Networks with Weak Informationcited by 25
  3. 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
  4. 2023Class-Imbalanced Learning on Graphs: A Surveycited by 24
  5. 2025A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detectioncited by 24
  6. 2022Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNscited by 23
  7. 2023Auto-HeG: Automated Graph Neural Network on Heterophilic Graphscited by 23
  8. 2024Graph Condensation: A Surveycited by 23
  9. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  10. 2023Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challengescited by 22
  11. 2023Permutation Equivariant Graph Framelets for Heterophilous Graph Learningcited by 19
  12. 2023A Neural Collapse Perspective on Feature Evolution in Graph Neural Networkscited by 19
  13. 2023Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classificationcited by 19
  14. 2022Node-oriented Spectral Filtering for Graph Neural Networkscited by 17
  15. 2023Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detectioncited by 17
  16. 2023GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labelscited by 17
  17. 2024OpenFGL: A Comprehensive Benchmark for Federated Graph Learningcited by 16
  18. 2022Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophilycited by 15
  19. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  20. 2022Projective Ranking-based GNN Evasion Attackscited by 14
  21. 2024Topology-aware Embedding Memory for Continual Learning on Expanding Networkscited by 14
  22. 2024A review of graph neural network applications in mechanics-related domainscited by 14
  23. 2022Link Prediction on Heterophilic Graphs via Disentangled Representation Learningcited by 13
  24. 2023TouchUp-G: Improving Feature Representation through Graph-Centric Finetuningcited by 12
  25. 2024Online GNN Evaluation Under Test-time Graph Distribution Shiftscited by 12
  26. 2024Continual Learning on Graphs: A Surveycited by 11
  27. 2024Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendationcited by 11
  28. 2024Exploring the Potential of Large Language Models for Heterophilic Graphscited by 10
  29. 2024On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networkscited by 10
  30. 2023GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropycited by 9
  31. 2024LOGIN: A Large Language Model Consulted Graph Neural Network Training Frameworkcited by 8
  32. 2024Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphscited by 8
  33. 2024Redesigning graph filter-based GNNs to relax the homophily assumptioncited by 8
  34. 2024Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Surveycited by 8
  35. 2026From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detectioncited by 8
  36. 2022Unsupervised Network Embedding Beyond Homophilycited by 7
  37. 2022Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagationcited by 7
  38. 2023Imbalanced Node Classification Beyond Homophilic Assumptioncited by 7

50 most cited of 175 All 175 (JSON)