mlsanityData to 7 Oct 2026

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

arXiv 2110.14446 ↗First posted 27 Oct 2021cs.LG cs.SI stat.MLcited by 309

Not on the map. Why?

Abstract (arXiv)

Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other. Recently, new Graph Neural Networks (GNNs) have been developed that move beyond the homophily regime; however, their evaluation has often been conducted on small graphs with limited application domains. We collect and introduce diverse non-homophilous datasets from a variety of application areas that have up to 384x more nodes and 1398x more edges than prior datasets. We further show that existing scalable graph learning and graph minibatching techniques lead to performance degradation on these non-homophilous datasets, thus highlighting the need for further work on scalable non-homophilous methods. To address these concerns, we introduce LINKX -- a strong simple method that admits straightforward minibatch training and inference. Extensive experimental results with representative simple methods and GNNs across our proposed datasets show that LINKX achieves state-of-the-art performance for learning on non-homophilous graphs. Our codes and data are available at https://github.com/CUAI/Non-Homophily-Large-Scale.

Key facts. Cited by 309 papers in the map (data through 7 Oct 2026). Builds on 45 of its 103 references that are in the map. First posted on arXiv 27 Oct 2021.

Builds on

45 of 103 references.

References · 45

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2017Inductive Representation Learning on Large Graphscited by 6,284
  7. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  10. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  11. 2019Simplifying Graph Convolutional Networkscited by 1,470
  12. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
33 more
  1. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  2. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  3. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  4. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  5. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  6. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  7. 2020Simple and Deep Graph Convolutional Networkscited by 857
  8. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  9. 2020Benchmarking Graph Neural Networkscited by 672
  10. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  11. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  12. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  13. 2019Multi-scale Attributed Node Embeddingcited by 543
  14. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  15. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  16. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  17. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  18. 2020Graph Neural Networks with Heterophilycited by 202
  19. 2020Combining Label Propagation and Simple Models Out-performs Graph Neural Networkscited by 199
  20. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  21. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  22. 2021The Values Encoded in Machine Learning Researchcited by 172
  23. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  24. 2020Non-Local Graph Neural Networkscited by 91
  25. 2019GraphZoom: A multi-level spectral approach for accurate and scalable graph embeddingcited by 58
  26. 2021Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddingscited by 48
  27. 2018Accurate, Efficient and Scalable Graph Embeddingcited by 35
  28. 2019Deep Surface Normal Estimation with Hierarchical RGB-D Fusioncited by 20
  29. 2020Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networkscited by 19
  30. 2020Expertise and Dynamics within Crowdsourced Musical Knowledge Curation: A Case Study of the Genius Platformcited by 13
  31. 2016Graph-based semi-supervised learning for relational networkscited by 10
  32. 2014Semi-Supervised Learning with Heterophilycited by 4
  33. 2020Stacked Graph Filtercited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 53; 2023: 63; 2024: 89; 2025: 60; 2026: 44.

309 papers.

Sort:

By area:

  1. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  2. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  3. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  4. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  5. 2023Specformer: Spectral Graph Neural Networks Meet Transformerscited by 102
  6. 2023Edge Directionality Improves Learning on Heterophilic Graphscited by 88
  7. 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
  8. 2024Position: Graph Foundation Models are Already Herecited by 84
  9. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 83
  10. 2024Polynormer: Polynomial-Expressive Graph Transformer in Linear Timecited by 64
  11. 2022DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detectioncited by 63
  12. 2022Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyondcited by 60
38 more
  1. 2022Understanding convolution on graphs via energiescited by 58
  2. 2022Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminatingcited by 57
  3. 2022GREAD: Graph Neural Reaction-Diffusion Networkscited by 54
  4. 2022Gradient Gating for Deep Multi-Rate Learning on Graphscited by 49
  5. 2023GSLB: The Graph Structure Learning Benchmarkcited by 49
  6. 2022Equivariant Hypergraph Diffusion Neural Operatorscited by 45
  7. 2022TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classificationcited by 41
  8. 2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
  9. 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 41
  10. 2023Simple and Asymmetric Graph Contrastive Learning without Augmentationscited by 37
  11. 2023Graph Neural Networks with Learnable and Optimal Polynomial Basescited by 36
  12. 2024VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connectionscited by 34
  13. 2023Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoderscited by 32
  14. 2022ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networkscited by 31
  15. 2023Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?cited by 31
  16. 2023OpenGSL: A Comprehensive Benchmark for Graph Structure Learningcited by 30
  17. 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clusteringcited by 29
  18. 2023PC-Conv: Unifying Homophily and Heterophily with Two-fold Filteringcited by 28
  19. 2022EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networkscited by 26
  20. 2022Model Inversion Attacks against Graph Neural Networkscited by 26
  21. 2022RAW-GNN: RAndom Walk Aggregation based Graph Neural Networkcited by 25
  22. 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
  23. 2022Graph Attention Retrospectivecited by 24
  24. 2023Towards Deep Attention in Graph Neural Networks: Problems and Remediescited by 24
  25. 2023Provably Powerful Graph Neural Networks for Directed Multigraphscited by 24
  26. 2024How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashingcited by 24
  27. 2022Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNscited by 23
  28. 2023HoloNets: Spectral Convolutions do extend to Directed Graphscited by 20
  29. 2024GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Datacited by 20
  30. 2022Improving Graph Neural Networks with Learnable Propagation Operatorscited by 19
  31. 2022Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Neural Networkscited by 19
  32. 2023Permutation Equivariant Graph Framelets for Heterophilous Graph Learningcited by 19
  33. 2023Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classificationcited by 19
  34. 2024Learning Graph Quantized Tokenizerscited by 19
  35. 2022Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networkscited by 18
  36. 2023Homophily-oriented Heterogeneous Graph Rewiringcited by 18
  37. 2023HomoGCL: Rethinking Homophily in Graph Contrastive Learningcited by 18
  38. 2024Learning Long Range Dependencies on Graphs via Random Walkscited by 18

50 most cited of 309 All 309 (JSON)