mlsanityData to 7 Oct 2026

Heterophily-Aware Graph Attention Network

arXiv 2302.03228 ↗First posted 7 Feb 2023cs.LG cs.SIcited by 7

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have shown remarkable success in graph representation learning. Unfortunately, current weight assignment schemes in standard GNNs, such as the calculation based on node degrees or pair-wise representations, can hardly be effective in processing the networks with heterophily, in which the connected nodes usually possess different labels or features. Existing heterophilic GNNs tend to ignore the modeling of heterophily of each edge, which is also a vital part in tackling the heterophily problem. In this paper, we firstly propose a heterophily-aware attention scheme and reveal the benefits of modeling the edge heterophily, i.e., if a GNN assigns different weights to edges according to different heterophilic types, it can learn effective local attention patterns, which enable nodes to acquire appropriate information from distinct neighbors. Then, we propose a novel Heterophily-Aware Graph Attention Network (HA-GAT) by fully exploring and utilizing the local distribution as the underlying heterophily, to handle the networks with different homophily ratios. To demonstrate the effectiveness of the proposed HA-GAT, we analyze the proposed heterophily-aware attention scheme and local distribution exploration, by seeking for an interpretation from their mechanism. Extensive results demonstrate that our HA-GAT achieves state-of-the-art performances on eight datasets with different homophily ratios in both the supervised and semi-supervised node classification tasks.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 7 Feb 2023.

Builds on

36 of 49 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  9. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  10. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  11. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  12. 2021How Attentive are Graph Attention Networks?cited by 818
24 more
  1. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  2. 2019Graph Transformer Networkscited by 520
  3. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  4. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  5. 2020Graph Neural Networks with Heterophilycited by 202
  6. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  7. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  8. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  9. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 164
  10. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  11. 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
  12. 2020GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learningcited by 113
  13. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  14. 2018Attention-based Graph Neural Network for Semi-supervised Learningcited by 100
  15. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  16. 2020Non-Local Graph Neural Networkscited by 91
  17. 2021GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophilycited by 84
  18. 2021Block Modeling-Guided Graph Convolutional Neural Networkscited by 32
  19. 2020Bi-GCN: Binary Graph Convolutional Networkcited by 27
  20. 2021Graph Pointer Neural Networkscited by 27
  21. 2022Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophilycited by 14
  22. 2018Graph Convolutional Neural Networks based on Quantum Vertex Saliencycited by 12
  23. 2022Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embeddingcited by 7
  24. 2022Binary Graph Convolutional Network with Capacity Explorationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 1; 2026: 1.

7 papers.

  1. 2024The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challengescited by 29
  2. 2024Understanding Heterophily for Graph Neural Networkscited by 15
  3. 2024A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directionscited by 13
  4. 2023CAT: A Causally Graph Attention Network for Trimming Heterophilic Graphcited by 2
  5. 2024Revisiting Neighborhood Aggregation in Graph Neural Networks for Node Classification using Statistical Signal Processingcited by 2
  6. 2025Topology-Aware Active Learning on Graphscited by 0
  7. 2026Gated Graph Attention Networks with Learnable Temperaturecited by 0