mlsanityData to 7 Oct 2026

A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness

arXiv 2406.09675 ↗First posted 14 Jun 2024cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

With recent advancements in graph neural networks (GNNs), spectral GNNs have received increasing popularity by virtue of their ability to retrieve graph signals in the spectral domain. These models feature uniqueness in efficient computation as well as rich expressiveness, which stems from advanced management and profound understanding of graph data. However, few systematic studies have been conducted to assess spectral GNNs, particularly in benchmarking their efficiency, memory consumption, and effectiveness in a unified and fair manner. There is also a pressing need to select spectral models suitable for learning specific graph data and deploying them to massive web-scale graphs, which is currently constrained by the varied model designs and training settings. In this work, we extensively benchmark spectral GNNs with a focus on the spectral perspective, demystifying them as spectral graph filters. We analyze and categorize 35 GNNs with 27 corresponding filters, spanning diverse formulations and utilizations of the graph data. Then, we implement the filters within a unified spectral-oriented framework with dedicated graph computations and efficient training schemes. In particular, our implementation enables the deployment of spectral GNNs over million-scale graphs and various tasks with comparable performance and less overhead. Thorough experiments are conducted on the graph filters with comprehensive metrics on effectiveness and efficiency, offering novel observations and practical guidelines that are only available from our evaluations across graph scales. Different from the prevailing belief, our benchmark reveals an intricate landscape regarding the effectiveness and efficiency of spectral graph filters, demonstrating the potential to achieve desirable performance through tailored spectral manipulation of graph data.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 89 of its 151 references that are in the map. First posted on arXiv 14 Jun 2024.

Builds on

89 of 151 references.

References · 89

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  9. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  10. 2019Simplifying Graph Convolutional Networkscited by 1,470
  11. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  12. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
38 more
  1. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  2. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  3. 2020Simple and Deep Graph Convolutional Networkscited by 857
  4. 2018Link Prediction Based on Graph Neural Networkscited by 829
  5. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  6. 2020Benchmarking Graph Neural Networkscited by 672
  7. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
  8. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  9. 2019Diffusion Improves Graph Learningcited by 414
  10. 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 409
  11. 2018Deep Learning on Graphs: A Surveycited by 393
  12. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  13. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  14. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  15. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
  16. 2020Towards Deeper Graph Neural Networkscited by 296
  17. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  18. 2015Diffusion-Convolutional Neural Networkscited by 268
  19. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  20. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  21. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  22. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  23. 2019AliGraph: A Comprehensive Graph Neural Network Platformcited by 152
  24. 2022NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphscited by 137
  25. 2019Graph Wavelet Neural Networkcited by 131
  26. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  27. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  28. 2023Specformer: Spectral Graph Neural Networks Meet Transformerscited by 102
  29. 2020Scalable Graph Neural Networks via Bidirectional Propagationcited by 87
  30. 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
  31. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 83
  32. 2019Stability and Generalization of Graph Convolutional Neural Networkscited by 81
  33. 2020Computing Graph Neural Networks: A Survey from Algorithms to Acceleratorscited by 81
  34. 2020Graph signal processing for machine learning: A review and new perspectivescited by 73
  35. 2022Hierarchical Graph Transformer with Adaptive Node Samplingcited by 72
  36. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  37. 2019GraphZoom: A multi-level spectral approach for accurate and scalable graph embeddingcited by 58
  38. 2021Dissecting the Diffusion Process in Linear Graph Convolutional Networkscited by 58

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 1.

6 papers.

  1. 2024The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challengescited by 29
  2. 2024Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphscited by 6
  3. 2025Spectro-Riemannian Graph Neural Networkscited by 5
  4. 2025When Deepfake Detection Meets Graph Neural Network:a Unified and Lightweight Learning Frameworkcited by 1
  5. 2025OpenGLT: A Comprehensive Benchmark of Graph Neural Networks for Graph-Level Taskscited by 0
  6. 2026Spectral Graph Neural Networks with Hermite Polynomials: A Comprehensive Studycited by 0