Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification

• URL: http://arxiv.org/abs/2406.08993v2
• Date: Mon, 28 Oct 2024 09:03:11 GMT
• Title: Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
• Authors: Yuankai Luo, Lei Shi, Xiao-Ming Wu,
• Abstract summary: Graph Transformers (GTs) have emerged as popular alternatives to traditional Graph Neural Networks (GNNs) In this paper, we reevaluate the performance of three classic GNN models (GCN, GAT, and GraphSAGE) against GTs.
• Score: 7.14327815822376
• License:
• Abstract: Graph Transformers (GTs) have recently emerged as popular alternatives to traditional message-passing Graph Neural Networks (GNNs), due to their theoretically superior expressiveness and impressive performance reported on standard node classification benchmarks, often significantly outperforming GNNs. In this paper, we conduct a thorough empirical analysis to reevaluate the performance of three classic GNN models (GCN, GAT, and GraphSAGE) against GTs. Our findings suggest that the previously reported superiority of GTs may have been overstated due to suboptimal hyperparameter configurations in GNNs. Remarkably, with slight hyperparameter tuning, these classic GNN models achieve state-of-the-art performance, matching or even exceeding that of recent GTs across 17 out of the 18 diverse datasets examined. Additionally, we conduct detailed ablation studies to investigate the influence of various GNN configurations, such as normalization, dropout, residual connections, and network depth, on node classification performance. Our study aims to promote a higher standard of empirical rigor in the field of graph machine learning, encouraging more accurate comparisons and evaluations of model capabilities.

Related papers

• PROXI: Challenging the GNNs for Link Prediction [3.8233569758620063]
  We introduce PROXI, which leverages proximity information of node pairs in both graph and attribute spaces. Standard machine learning (ML) models perform competitively, even outperforming cutting-edge GNN models. We show that augmenting traditional GNNs with PROXI significantly boosts their link prediction performance.
  arXiv  Detail & Related papers  (2024-10-02T17:57:38Z)
• A Manifold Perspective on the Statistical Generalization of Graph Neural Networks [84.01980526069075]
  We take a manifold perspective to establish the statistical generalization theory of GNNs on graphs sampled from a manifold in the spectral domain. We prove that the generalization bounds of GNNs decrease linearly with the size of the graphs in the logarithmic scale, and increase linearly with the spectral continuity constants of the filter functions.
  arXiv  Detail & Related papers  (2024-06-07T19:25:02Z)
• 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)
• How Expressive are Graph Neural Networks in Recommendation? [17.31401354442106]
  Graph Neural Networks (GNNs) have demonstrated superior performance on various graph learning tasks, including recommendation. Recent research has explored the expressiveness of GNNs in general, demonstrating that message passing GNNs are at most as powerful as the Weisfeiler-Lehman test. We propose the topological closeness metric to evaluate GNNs' ability to capture the structural distance between nodes.
  arXiv  Detail & Related papers  (2023-08-22T02:17:34Z)
• Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs [71.93227401463199]
  This paper pinpoints the major source of GNNs' performance gain to their intrinsic capability, by introducing an intermediate model class dubbed as P(ropagational)MLP. We observe that PMLPs consistently perform on par with (or even exceed) their GNN counterparts, while being much more efficient in training.
  arXiv  Detail & Related papers  (2022-12-18T08:17:32Z)
• 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)
• Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels [25.736529232578178]
  Graph neural networks (GNNs) have achieved tremendous success in graph mining. MPGNNs, as the prevailing type of GNNs, have been theoretically shown unable to distinguish, detect or count many graph substructures. We propose GSKN, a GNN model with a theoretically stronger ability to distinguish graph structures.
  arXiv  Detail & Related papers  (2021-04-07T08:50:34Z)
• Learning to Drop: Robust Graph Neural Network via Topological Denoising [50.81722989898142]
  We propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of Graph Neural Networks (GNNs) PTDNet prunes task-irrelevant edges by penalizing the number of edges in the sparsified graph with parameterized networks. We show that PTDNet can improve the performance of GNNs significantly and the performance gain becomes larger for more noisy datasets.
  arXiv  Detail & Related papers  (2020-11-13T18:53:21Z)
• The Surprising Power of Graph Neural Networks with Random Node Initialization [54.4101931234922]
  Graph neural networks (GNNs) are effective models for representation learning on relational data. Standard GNNs are limited in their expressive power, as they cannot distinguish beyond the capability of the Weisfeiler-Leman graph isomorphism. In this work, we analyze the expressive power of GNNs with random node (RNI) We prove that these models are universal, a first such result for GNNs not relying on computationally demanding higher-order properties.
  arXiv  Detail & Related papers  (2020-10-02T19:53:05Z)
• Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs [20.197085398581397]
  Graph neural networks (GNNs) have received much attention recently because of their excellent performance on graph-based tasks. We propose self-enhanced GNN (SEG), which improves the quality of the input data using the outputs of existing GNN models. SEG consistently improves the performance of well-known GNN models such as GCN, GAT and SGC across different datasets.
  arXiv  Detail & Related papers  (2020-02-18T12:27:16Z)

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.