Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs

• URL: http://arxiv.org/abs/2212.09034v4
• Date: Fri, 4 Aug 2023 05:08:44 GMT
• Title: Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs
• Authors: Chenxiao Yang, Qitian Wu, Jiahua Wang, Junchi Yan
• Abstract summary: 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.
• Score: 71.93227401463199
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph neural networks (GNNs), as the de-facto model class for representation learning on graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional message passing layers to allow features to flow across nodes. While conventional wisdom commonly attributes the success of GNNs to their advanced expressivity, we conjecture that this is not the main cause of GNNs' superiority in node-level prediction tasks. This paper pinpoints the major source of GNNs' performance gain to their intrinsic generalization capability, by introducing an intermediate model class dubbed as P(ropagational)MLP, which is identical to standard MLP in training, but then adopts GNN's architecture in testing. Intriguingly, we observe that PMLPs consistently perform on par with (or even exceed) their GNN counterparts, while being much more efficient in training. This finding sheds new insights into understanding the learning behavior of GNNs, and can be used as an analytic tool for dissecting various GNN-related research problems. As an initial step to analyze the inherent generalizability of GNNs, we show the essential difference between MLP and PMLP at infinite-width limit lies in the NTK feature map in the post-training stage. Moreover, by examining their extrapolation behavior, we find that though many GNNs and their PMLP counterparts cannot extrapolate non-linear functions for extremely out-of-distribution samples, they have greater potential to generalize to testing samples near the training data range as natural advantages of GNN architectures.

Related papers

• Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias [75.44877675117749]
  We propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph datasets Benchmark.
  arXiv  Detail & Related papers  (2023-09-26T13:09:43Z)
• GNN-Ensemble: Towards Random Decision Graph Neural Networks [3.7620848582312405]
  Graph Neural Networks (GNNs) have enjoyed wide spread applications in graph-structured data. GNNs are required to learn latent patterns from a limited amount of training data to perform inferences on a vast amount of test data. In this paper, we push one step forward on the ensemble learning of GNNs with improved accuracy, robustness, and adversarial attacks.
  arXiv  Detail & Related papers  (2023-03-20T18:24:01Z)
• Superiority of GNN over NN in generalizing bandlimited functions [6.3151583550712065]
  Graph Neural Networks (GNNs) have emerged as formidable resources for processing graph-based information across diverse applications. In this study, we investigate the proficiency of GNNs for such classifications, which can also be cast as a function problem. Our findings highlight a pronounced efficiency in utilizing GNNs to generalize a bandlimited function within an $varepsilon$-error margin.
  arXiv  Detail & Related papers  (2022-06-13T05:15:12Z)
• Subgroup Generalization and Fairness of Graph Neural Networks [12.88476464580968]
  We present a novel PAC-Bayesian analysis for GNNs under a non-IID semi-supervised learning setup. We further study an accuracy-(dis)parity-style (un)fairness of GNNs from a theoretical perspective.
  arXiv  Detail & Related papers  (2021-06-29T16:13:41Z)
• Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth [57.10183643449905]
  Graph Neural Networks (GNNs) have been studied from the lens of expressive power and generalization. We study the dynamics of GNNs by studying deep skip optimization. Our results provide first theoretical support for the success of GNNs.
  arXiv  Detail & Related papers  (2021-05-10T17:59:01Z)
• 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)
• How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks [80.55378250013496]
  We study how neural networks trained by gradient descent extrapolate what they learn outside the support of the training distribution. Graph Neural Networks (GNNs) have shown some success in more complex tasks.
  arXiv  Detail & Related papers  (2020-09-24T17:48:59Z)
• Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs [95.63153473559865]
  Graph Neural Networks (GNNs) are emerging machine learning models on graphs. Most existing GNN models in practice are shallow and essentially feature-centric. We show empirically and analytically that the existing shallow GNNs cannot preserve graph structures well. We propose Eigen-GNN, a plug-in module to boost GNNs ability in preserving graph structures.
  arXiv  Detail & Related papers  (2020-06-08T02:47:38Z)

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.