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

• URL: http://arxiv.org/abs/2406.09675v3
• Date: Wed, 20 Aug 2025 07:15:59 GMT
• Title: A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness
• Authors: Ningyi Liao, Haoyu Liu, Zulun Zhu, Siqiang Luo, Laks V. S. Lakshmanan,
• Abstract summary: spectral neural networks (GNNs) have received increasing popularity by virtue of their ability to retrieve graph signals in the spectral domain.<n>We extensively benchmark spectral GNNs with a focus on the spectral perspective, demystifying them as spectral graph filters.<n>We implement the filters within a unified spectral-oriented framework with dedicated graph computations and efficient training schemes.
• Score: 20.518170371888075
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Large-Scale Spectral Graph Neural Networks via Laplacian Sparsification: Technical Report [21.288230563135055]
  We propose a novel graph spectral sparsification method to approximate the propagation patterns of spectral Graph Neural Networks (GNNs) Our method allows the application of linear layers on the input node features, enabling end-to-end training as well as the handling of raw features.
  arXiv  Detail & Related papers  (2025-01-08T15:36:19Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs) This framework provides a standardized setting to evaluate GNNs across diverse datasets. We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks [6.755403881158429]
  We propose AutoSGNN, an automated framework for discovering propagation mechanisms in spectral GNNs. We show that AutoSGNN outperforms state-of-the-art spectral GNNs and graph neural architecture search methods in both performance and efficiency.
  arXiv  Detail & Related papers  (2024-12-17T02:37:48Z)
• Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective [49.613774305350084]
  Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based learning tasks. Recent studies suggest that other components such as non-linear layers may also significantly affect how GNNs process the input graph data in the spectral domain. 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.
  arXiv  Detail & Related papers  (2024-12-10T04:53:53Z)
• GrassNet: State Space Model Meets Graph Neural Network [57.62885438406724]
  Graph State Space Network (GrassNet) is a novel graph neural network with theoretical support that provides a simple yet effective scheme for designing arbitrary graph spectral filters. To the best of our knowledge, our work is the first to employ SSMs for the design of graph GNN spectral filters. Extensive experiments on nine public benchmarks reveal that GrassNet achieves superior performance in real-world graph modeling tasks.
  arXiv  Detail & Related papers  (2024-08-16T07:33:58Z)
• Characterizing and Understanding HGNN Training on GPUs [9.579848162902628]
  Heterogeneous Graph Neural Networks (HGNNs) have been widely adopted in many real-world domains such as recommendation systems and medical analysis. To enhance the efficiency of HGNN training, it is essential to characterize and analyze the execution semantics and patterns within the training process to identify performance bottlenecks.
  arXiv  Detail & Related papers  (2024-07-16T14:45:46Z)
• Spectral Greedy Coresets for Graph Neural Networks [61.24300262316091]
  The ubiquity of large-scale graphs in node-classification tasks hinders the real-world applications of Graph Neural Networks (GNNs) This paper studies graph coresets for GNNs and avoids the interdependence issue by selecting ego-graphs based on their spectral embeddings. Our spectral greedy graph coreset (SGGC) scales to graphs with millions of nodes, obviates the need for model pre-training, and applies to low-homophily graphs.
  arXiv  Detail & Related papers  (2024-05-27T17:52:12Z)
• GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels [81.93520935479984]
  We study a new problem, GNN model evaluation, that aims to assess the performance of a specific GNN model trained on labeled and observed graphs. We propose a two-stage GNN model evaluation framework, including (1) DiscGraph set construction and (2) GNNEvaluator training and inference. Under the effective training supervision from the DiscGraph set, GNNEvaluator learns to precisely estimate node classification accuracy of the to-be-evaluated GNN model.
  arXiv  Detail & Related papers  (2023-10-23T05:51:59Z)
• Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis [50.972595036856035]
  We present a code that successfully replicates results from six popular and recent graph recommendation models. We compare these graph models with traditional collaborative filtering models that historically performed well in offline evaluations. By investigating the information flow from users' neighborhoods, we aim to identify which models are influenced by intrinsic features in the dataset structure.
  arXiv  Detail & Related papers  (2023-08-01T09:31:44Z)
• Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting [101.5022396668152]
  Spectral-temporal graph neural network is a promising abstraction underlying most time series forecasting models. We establish a theoretical framework that unravels the expressive power of spectral-temporal GNNs. Our findings pave the way for devising a broader array of provably expressive GNN-based models for time series.
  arXiv  Detail & Related papers  (2023-05-11T05:56:38Z)
• Characterizing the Efficiency of Graph Neural Network Frameworks with a Magnifying Glass [10.839902229218577]
  Graph neural networks (GNNs) have received great attention due to their success in various graph-related learning tasks. Recent GNNs have been developed with different graph sampling techniques for mini-batch training of GNNs on large graphs. It is unknown how much the frameworks are 'eco-friendly' from a green computing perspective.
  arXiv  Detail & Related papers  (2022-11-06T04:22:19Z)
• EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks [51.42338058718487]
  Graph Neural Networks (GNNs) have received extensive research attention for their promising performance in graph machine learning. Existing approaches, such as GCN and GPRGNN, are not robust in the face of homophily changes on test graphs. We propose EvenNet, a spectral GNN corresponding to an even-polynomial graph filter.
  arXiv  Detail & Related papers  (2022-05-27T10:48:14Z)
• Quasi-Framelets: Robust Graph Neural Networks via Adaptive Framelet Convolution [28.474359021962346]
  We propose a multiscale framelet convolution for spectral graph neural networks (GNNs) The proposed design excels in filtering out unwanted spectral information and significantly reduces the adverse effects of noisy graph signals. It exhibits remarkable resilience to noisy data and adversarial attacks, highlighting its potential as a robust solution for real-world graph applications.
  arXiv  Detail & Related papers  (2022-01-11T00:10:28Z)
• Attention-Based Recommendation On Graphs [9.558392439655012]
  Graph Neural Networks (GNN) have shown remarkable performance in different tasks. In this study, we propose GARec as a model-based recommender system. The presented method outperforms existing model-based, non-graph neural networks and graph neural networks in different MovieLens datasets.
  arXiv  Detail & Related papers  (2022-01-04T21:02:02Z)
• Pointspectrum: Equivariance Meets Laplacian Filtering for Graph Representation Learning [3.7875603451557063]
  Graph Representation Learning (GRL) has become essential for modern graph data mining and learning tasks. While Graph Neural Networks (GNNs) have been used in state-of-the-art GRL architectures, they have been shown to suffer from over smoothing. We propose PointSpectrum, a spectral method that incorporates a set equivariant network to account for a graph's structure.
  arXiv  Detail & Related papers  (2021-09-06T10:59:11Z)
• Robust Optimization as Data Augmentation for Large-scale Graphs [117.2376815614148]
  We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks.
  arXiv  Detail & Related papers  (2020-10-19T21:51:47Z)
• Spectral Graph Attention Network with Fast Eigen-approximation [103.93113062682633]
  Spectral Graph Attention Network (SpGAT) learns representations for different frequency components regarding weighted filters and graph wavelets bases. Fast approximation variant SpGAT-Cheby is proposed to reduce the computational cost brought by the eigen-decomposition. We thoroughly evaluate the performance of SpGAT and SpGAT-Cheby in semi-supervised node classification tasks.
  arXiv  Detail & Related papers  (2020-03-16T21:49:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.