mlsanityData to 14 Oct 2026

Heterophily-informed Message Passing

arXiv 2504.19785 ↗First posted 28 Apr 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) are known to be vulnerable to oversmoothing due to their implicit homophily assumption. We mitigate this problem with a novel scheme that regulates the aggregation of messages, modulating the type and extent of message passing locally thereby preserving both the low and high-frequency components of information. Our approach relies solely on learnt embeddings, obviating the need for auxiliary labels, thus extending the benefits of heterophily-aware embeddings to broader applications, e.g., generative modelling. Our experiments, conducted across various data sets and GNN architectures, demonstrate performance enhancements and reveal heterophily patterns across standard classification benchmarks. Furthermore, application to molecular generation showcases notable performance improvements on chemoinformatics benchmarks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 47 of its 66 references that are in the map. First posted on arXiv 28 Apr 2025.

Builds on

47 of 66 references.

References · 47

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  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. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  9. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  10. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  12. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
35 more
  1. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  2. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  3. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
  4. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  5. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  6. 2019Multi-scale Attributed Node Embeddingcited by 548
  7. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  8. 2018MolGAN: An implicit generative model for small molecular graphscited by 393
  9. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 364
  10. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  11. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
  12. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
  13. 2017Grammar Variational Autoencodercited by 285
  14. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 275
  15. 2020Generalization and Representational Limits of Graph Neural Networkscited by 218
  16. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 214
  17. 2020Graph Neural Networks with Heterophilycited by 202
  18. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 186
  19. 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 185
  20. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  21. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  22. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 180
  23. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  24. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  25. 2016Discriminative Embeddings of Latent Variable Models for Structured Datacited by 131
  26. 2017Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Modelscited by 117
  27. 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
  28. 2020Non-Local Graph Neural Networkscited by 91
  29. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  30. 2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
  31. 2021Tree Decomposed Graph Neural Networkcited by 35
  32. 2022ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networkscited by 31
  33. 2015Homophily and missing links in citation networkscited by 21
  34. 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
  35. 2022Modular Flows: Differential Molecular Generationcited by 11

Built on by

Not cited yet.