mlsanityData to 14 Oct 2026

Label-Wise Graph Convolutional Network for Heterophilic Graphs

arXiv 2110.08128 ↗First posted 15 Oct 2021cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved remarkable performance in modeling graphs for various applications. However, most existing GNNs assume the graphs exhibit strong homophily in node labels, i.e., nodes with similar labels are connected in the graphs. They fail to generalize to heterophilic graphs where linked nodes may have dissimilar labels and attributes. Therefore, in this paper, we investigate a novel framework that performs well on graphs with either homophily or heterophily. More specifically, we propose a label-wise message passing mechanism to avoid the negative effects caused by aggregating dissimilar node representations and preserve the heterophilic contexts for representation learning. We further propose a bi-level optimization method to automatically select the model for graphs with homophily/heterophily. Theoretical analysis and extensive experiments demonstrate the effectiveness of our proposed framework for node classification on both homophilic and heterophilic graphs.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 37 of its 50 references that are in the map. First posted on arXiv 15 Oct 2021.

Builds on

37 of 50 references.

References · 37

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  7. 2019Simplifying Graph Convolutional Networkscited by 1,477
  8. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  9. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  10. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  11. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  12. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
25 more
  1. 2020Simple and Deep Graph Convolutional Networkscited by 860
  2. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  3. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  4. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  5. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  6. 2019Multi-scale Attributed Node Embeddingcited by 548
  7. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  8. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  9. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  10. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  11. 2016Learning Convolutional Neural Networks for Graphscited by 314
  12. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 250
  13. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  14. 2020Graph Neural Networks with Heterophilycited by 202
  15. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  16. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  17. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 151
  18. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  19. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  20. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  21. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  22. 2020Molecular graph generation with Graph Neural Networkscited by 80
  23. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  24. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  25. 2021Semi-Supervised Graph-to-Graph Translationcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 6; 2025: 1; 2026: 1.

17 papers.

Sort:

  1. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  2. 2023Unnoticeable Backdoor Attacks on Graph Neural Networkscited by 45
  3. 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
  4. 2023Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classificationcited by 19
  5. 2023A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacycited by 14
  6. 2024Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphscited by 8
  7. 2023Spatial Heterophily Aware Graph Neural Networkscited by 7
  8. 2024Robustness Inspired Graph Backdoor Defensecited by 7
  9. 2023Shape-aware Graph Spectral Learningcited by 6
  10. 2024The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphscited by 6
  11. 2023Clarify Confused Nodes via Separated Learningcited by 5
  12. 2024Heterophilic Graph Neural Networks Optimization with Causal Message-passingcited by 4
5 more
  1. 2025GraphSOS: Graph Sampling and Order Selection to Help LLMs Understand Graphs Bettercited by 4
  2. 2023CAT: A Causally Graph Attention Network for Trimming Heterophilic Graphcited by 2
  3. 2024Edge-Splitting MLP: Node Classification on Homophilic and Heterophilic Graphs without Message Passingcited by 2
  4. 2023ElegansNet: a brief scientific report and initial experimentscited by 0
  5. 2026Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attackscited by 0