mlsanityData to 14 Oct 2026

Incorporating Heterophily into Graph Neural Networks for Graph Classification

arXiv 2203.07678 ↗First posted 15 Mar 2022cs.LG cs.SIcited by 4

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) often assume strong homophily for graph classification, seldom considering heterophily, which means connected nodes tend to have different class labels and dissimilar features. In real-world scenarios, graphs may have nodes that exhibit both homophily and heterophily. Failing to generalize to this setting makes many GNNs underperform in graph classification. In this paper, we address this limitation by identifying three effective designs and develop a novel GNN architecture called IHGNN (short for Incorporating Heterophily into Graph Neural Networks). These designs include the combination of integration and separation of the ego- and neighbor-embeddings of nodes, adaptive aggregation of node embeddings from different layers, and differentiation between different node embeddings for constructing the graph-level readout function. We empirically validate IHGNN on various graph datasets and demonstrate that it outperforms the state-of-the-art GNNs for graph classification.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 48 of its 94 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

48 of 94 references.

References · 48

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  8. 2019Simplifying Graph Convolutional Networkscited by 1,477
  9. 2017Deep Setscited by 1,421
  10. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  11. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  12. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
36 more
  1. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  2. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
  3. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  4. 2015Gated Graph Sequence Neural Networkscited by 796
  5. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  6. 2020Benchmarking Graph Neural Networkscited by 680
  7. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  8. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 561
  9. 2019Provably Powerful Graph Networkscited by 389
  10. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  11. 2018Invariant and Equivariant Graph Networkscited by 346
  12. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 329
  13. 2016Learning Convolutional Neural Networks for Graphscited by 314
  14. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
  15. 2015Diffusion-Convolutional Neural Networkscited by 268
  16. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
  17. 2021GRAND: Graph Neural Diffusioncited by 258
  18. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  19. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  20. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  21. 2018Attention-based Graph Neural Network for Semi-supervised Learningcited by 101
  22. 2021Breaking the Limits of Message Passing Graph Neural Networkscited by 101
  23. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  24. 2014Propagation Kernelscited by 88
  25. 2020Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networkscited by 77
  26. 2019LanczosNet: Multi-Scale Deep Graph Convolutional Networkscited by 73
  27. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  28. 2022Simplified Graph Convolution with Heterophilycited by 17
  29. 2017On the expressive power of query languages for matricescited by 14
  30. 2018On the expressive power of linear algebra on graphscited by 14
  31. 2022An Exploratory Study of Stock Price Movements from Earnings Callscited by 14
  32. 2020Hierarchical Graph Capsule Networkcited by 11
  33. 2020Tree++: Truncated Tree Based Graph Kernelscited by 4
  34. 2021Event Detection on Dynamic Graphscited by 4
  35. 2020Learning Deep Graph Representations via Convolutional Neural Networkscited by 3
  36. 2022Graph Neural Diffusion Networks for Semi-supervised Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 1.

4 papers.

  1. 2024The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challengescited by 29
  2. 2024Transfer Entropy in Graph Convolutional Neural Networkscited by 1
  3. 2025Preference-driven Knowledge Distillation for Few-shot Node Classificationcited by 1
  4. 2024Flexible Infinite-Width Graph Convolutional Neural Networkscited by 0