mlsanityData to 14 Oct 2026

Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective

arXiv 2412.07188 ↗First posted 10 Dec 2024cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based learning tasks. While their performance is often attributed to the powerful neighborhood aggregation mechanism, recent studies suggest that other components such as non-linear layers may also significantly affecting how GNNs process the input graph data in the spectral domain. Such evidence challenges the prevalent opinion that neighborhood aggregation mechanisms dominate the behavioral characteristics of GNNs in the spectral domain. To demystify such a conflict, this paper introduces a comprehensive benchmark to measure and evaluate GNNs' capability in capturing and leveraging the information encoded in different frequency components of the input graph data. Specifically, we first conduct an exploratory study demonstrating that GNNs can flexibly yield outputs with diverse frequency components even when certain frequencies are absent or filtered out from the input graph data. We then formulate a novel research problem of measuring and benchmarking the performance of GNNs from a spectral perspective. To take an initial step towards a comprehensive benchmark, we design an evaluation protocol supported by comprehensive theoretical analysis. Finally, we introduce a comprehensive benchmark on real-world datasets, revealing insights that challenge prevalent opinions from a spectral perspective. We believe that our findings will open new avenues for future advancements in this area. Our implementations can be found at: https://github.com/yushundong/Spectral-benchmark.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 43 of its 55 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

43 of 55 references.

References · 43

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  8. 2019Simplifying Graph Convolutional Networkscited by 1,477
  9. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  10. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  11. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  12. 2020Simple and Deep Graph Convolutional Networkscited by 860
31 more
  1. 2021How Attentive are Graph Attention Networks?cited by 835
  2. 2015Gated Graph Sequence Neural Networkscited by 796
  3. 2019Graph Neural Networks for Social Recommendationcited by 714
  4. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  5. 2020Benchmarking Graph Neural Networkscited by 680
  6. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  7. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  8. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  9. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
  10. 2022Long Range Graph Benchmarkcited by 263
  11. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
  12. 2020Graph Neural Networks with Heterophilycited by 202
  13. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  14. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 187
  15. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  16. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  17. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  18. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  19. 2021Spherical Message Passing for 3D Graph Networkscited by 168
  20. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  21. 2021Breaking the Limits of Message Passing Graph Neural Networkscited by 101
  22. 2022Theory of Graph Neural Networks: Representation and Learningcited by 61
  23. 2023Does Graph Distillation See Like Vision Dataset Counterpart?cited by 45
  24. 2021Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learningcited by 44
  25. 2021AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filtercited by 43
  26. 2020Graph Convolutional Network for Recommendation with Low-pass Collaborative Filterscited by 32
  27. 2022High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancingcited by 26
  28. 2023A Survey on Spectral Graph Neural Networkscited by 26
  29. 2021A New Perspective on the Effects of Spectrum in Graph Neural Networkscited by 24
  30. 2023Graph Neural Networks with Diverse Spectral Filteringcited by 9
  31. 2024GNNBENCH: Fair and Productive Benchmarking for Single-GPU GNN Systemcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisitioncited by 10
  2. 2026A Spectral Decomposition Framework for Multiscale Nonlinear Dimensionality Reductioncited by 0
  3. 2026SPR: Toward a Graph Foundation Model for Transferable Graph Cognition via Spectral Patterns and Relational Geometrycited by 0