mlsanityData to 7 Oct 2026

Homophily-oriented Heterogeneous Graph Rewiring

arXiv 2302.06299 ↗First posted 13 Feb 2023cs.SI cs.AI cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

With the rapid development of the World Wide Web (WWW), heterogeneous graphs (HG) have explosive growth. Recently, heterogeneous graph neural network (HGNN) has shown great potential in learning on HG. Current studies of HGNN mainly focus on some HGs with strong homophily properties (nodes connected by meta-path tend to have the same labels), while few discussions are made in those that are less homophilous. Recently, there have been many works on homogeneous graphs with heterophily. However, due to heterogeneity, it is non-trivial to extend their approach to deal with HGs with heterophily. In this work, based on empirical observations, we propose a meta-path-induced metric to measure the homophily degree of a HG. We also find that current HGNNs may have degenerated performance when handling HGs with less homophilous properties. Thus it is essential to increase the generalization ability of HGNNs on non-homophilous HGs. To this end, we propose HDHGR, a homophily-oriented deep heterogeneous graph rewiring approach that modifies the HG structure to increase the performance of HGNN. We theoretically verify HDHGR. In addition, experiments on real-world HGs demonstrate the effectiveness of HDHGR, which brings at most more than 10% relative gain.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 46 of its 81 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

46 of 81 references.

References · 46

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  4. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  5. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  6. 2019Heterogeneous Graph Attention Networkcited by 732
  7. 2020Heterogeneous Graph Transformercited by 581
  8. 2019Graph Transformer Networkscited by 520
  9. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
  10. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  11. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  12. 2017"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detectioncited by 361
34 more
  1. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  2. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  3. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  4. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  5. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  6. 2020Graph Neural Networks with Heterophilycited by 202
  7. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  8. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  9. 2022Towards Unsupervised Deep Graph Structure Learningcited by 112
  10. 2020Heterogeneous Graph Neural Networks for Malicious Account Detectioncited by 95
  11. 2021GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophilycited by 84
  12. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  13. 2019An Attention-based Graph Neural Network for Heterogeneous Structural Learningcited by 71
  14. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  15. 2021AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filtercited by 43
  16. 2022Efficiently Leveraging Multi-level User Intent for Session-based Recommendation via Atten-Mixer Networkcited by 38
  17. 2020Representation Based Complexity Measures for Predicting Generalization in Deep Learningcited by 29
  18. 2022Multiplex Heterogeneous Graph Convolutional Networkcited by 27
  19. 2020On the Stability of Graph Convolutional Neural Networks under Edge Rewiringcited by 25
  20. 2022Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approachcited by 23
  21. 2021Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendationcited by 22
  22. 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
  23. 2021Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphscited by 18
  24. 2021Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophilycited by 14
  25. 2022Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophilycited by 14
  26. 2022Price DOES Matter! Modeling Price and Interest Preferences in Session-based Recommendationcited by 11
  27. 2022Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendationcited by 11
  28. 2022MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distributioncited by 11
  29. 2016Graph-based semi-supervised learning for relational networkscited by 10
  30. 2023Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networkscited by 10
  31. 2022Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Networkcited by 8
  32. 2021Deformable Graph Convolutional Networkscited by 6
  33. 2022On Graph Neural Network Fairness in the Presence of Heterophilous Neighborhoodscited by 6
  34. 2022Graph Representation Learning Beyond Node and Homophilycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 8; 2025: 4; 2026: 1.

18 papers.

Sort:

  1. 2024A Comprehensive Survey on Data Augmentationcited by 38
  2. 2023Continual Learning on Dynamic Graphs via Parameter Isolationcited by 35
  3. 2023Permutation Equivariant Graph Framelets for Heterophilous Graph Learningcited by 19
  4. 2024A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directionscited by 13
  5. 2024When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learningcited by 12
  6. 2023Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfercited by 10
  7. 2023On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filteringcited by 9
  8. 2023Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometriescited by 6
  9. 2024Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Networkcited by 3
  10. 2025Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneitycited by 3
  11. 2024LSPI: Heterogeneous Graph Neural Network Classification Aggregation Algorithm Based on Size Neighbor Path Identificationcited by 2
  12. 2025Heterogeneous Graph Structure Learning through the Lens of Data-generating Processescited by 2
6 more
  1. 2025Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphscited by 2
  2. 2024Message Detouring: A Simple Yet Effective Cycle Representation for Expressive Graph Learningcited by 0
  3. 2024LAMP: Learnable Meta-Path Guided Adversarial Contrastive Learning for Heterogeneous Graphscited by 0
  4. 2024Graph as a feature: improving node classification with non-neural graph-aware logistic regressioncited by 0
  5. 2025Are Heterogeneous Graph Neural Networks Truly Effective for Node Classification? A Causal Perspectivecited by 0
  6. 2026Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learningcited by 0