mlsanityData to 14 Oct 2026

Block Modeling-Guided Graph Convolutional Neural Networks

arXiv 2112.13507 ↗First posted 27 Dec 2021cs.LG cs.SIcited by 32

Not on the map. Why?

Abstract (arXiv)

Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation. However, the GCN aggregating mechanism fails to generalize to networks with heterophily where most nodes have neighbors from different classes, which commonly exists in real-world networks. In order to make the propagation and aggregation mechanism of GCN suitable for both homophily and heterophily (or even their mixture), we introduce block modeling into the framework of GCN so that it can realize "block-guided classified aggregation", and automatically learn the corresponding aggregation rules for neighbors of different classes. By incorporating block modeling into the aggregation process, GCN is able to aggregate information from homophilic and heterophilic neighbors discriminately according to their homophily degree. We compared our algorithm with state-of-art methods which deal with the heterophily problem. Empirical results demonstrate the superiority of our new approach over existing methods in heterophilic datasets while maintaining a competitive performance in homophilic datasets.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 27 Dec 2021.

Builds on

21 of 33 references.

References · 21

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  3. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  5. 2019Simplifying Graph Convolutional Networkscited by 1,477
  6. 2016Variational Graph Auto-Encoderscited by 1,382
  7. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  8. 2018Link Prediction Based on Graph Neural Networkscited by 832
  9. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  10. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  11. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  12. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
9 more
  1. 2019Multi-scale Attributed Node Embeddingcited by 548
  2. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  3. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
  4. 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
  5. 2020Graph Neural Networks with Heterophilycited by 202
  6. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  7. 2017A Survey on Network Embeddingcited by 142
  8. 2021A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learningcited by 55
  9. 2020Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designscited by 25

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 10; 2024: 7; 2025: 7; 2026: 2.

32 papers.

Sort:

By area:

  1. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  2. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  3. 2022RAW-GNN: RAndom Walk Aggregation based Graph Neural Networkcited by 25
  4. 2022Node-oriented Spectral Filtering for Graph Neural Networkscited by 17
  5. 2024Understanding Heterophily for Graph Neural Networkscited by 15
  6. 2022HP-GMN: Graph Memory Networks for Heterophilous Graphscited by 13
  7. 2023GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropycited by 9
  8. 2023Heterophily-Aware Graph Attention Networkcited by 7
  9. 2023Spatial Heterophily Aware Graph Neural Networkscited by 7
  10. 2024Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detectioncited by 7
  11. 2023Shape-aware Graph Spectral Learningcited by 6
  12. 2024Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shiftscited by 6
20 more
  1. 2023SignGT: Signed Attention-based Graph Transformer for Graph Representation Learningcited by 5
  2. 2024NTFormer: A Composite Node Tokenized Graph Transformer for Node Classificationcited by 5
  3. 2025Rethinking Tokenized Graph Transformers for Node Classificationcited by 5
  4. 2023GCNH: A Simple Method For Representation Learning On Heterophilous Graphscited by 4
  5. 2023GPatcher: A Simple and Adaptive MLP Model for Alleviating Graph Heterophilycited by 3
  6. 2025HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relationscited by 3
  7. 2024HC-GST: Heterophily-aware Distribution Consistency based Graph Self-trainingcited by 2
  8. 2023Self-attention Dual Embedding for Graphs with Heterophilycited by 1
  9. 2022Propagation with Adaptive Mask then Training for Node Classification on Attributed Networkscited by 0
  10. 2022Neighborhood Convolutional Network: A New Paradigm of Graph Neural Networks for Node Classificationcited by 0
  11. 2023Evolving Computation Graphscited by 0
  12. 2024Boosting Graph Foundation Model from Structural Perspectivecited by 0
  13. 2024Dual-Frequency Filtering Self-aware Graph Neural Networks for Homophilic and Heterophilic Graphscited by 0
  14. 2025Directed Homophily-Aware Graph Neural Networkcited by 0
  15. 2025Aggregation-aware MLP: An Unsupervised Approach for Graph Message-passingcited by 0
  16. 2025Gumbel-MPNN: Graph Rewiring with Gumbel-Softmaxcited by 0
  17. 2025Learning from Heterophilic Graphs: A Spectral Theory Perspective on the Impact of Self-Loops and Parallel Edgescited by 0
  18. 2025Bridging Computational Social Science and Deep Learning: Cultural Dissemination-Inspired Graph Neural Networkscited by 0
  19. 2026ASPECT: Node-Level Adaptive Spectral Fusion for Graph Contrastive Learningcited by 0
  20. 2026Robust Contrastive Graph Clustering with Adaptive Local-Global Integrationcited by 0