Size Generalization of Graph Neural Networks on Biological Data: Insights and Practices from the Spectral Perspective

• URL: http://arxiv.org/abs/2305.15611v4
• Date: Wed, 7 Feb 2024 03:27:12 GMT
• Title: Size Generalization of Graph Neural Networks on Biological Data: Insights and Practices from the Spectral Perspective
• Authors: Gaotang Li, Danai Koutra, Yujun Yan
• Abstract summary: We investigate size-induced distribution shifts in graphs and assess their impact on the ability of graph neural networks (GNNs) to generalize to larger graphs. We introduce a simple yet effective model-agnostic strategy, which makes GNNs aware of important subgraph patterns to enhance their size generalizability.
• Score: 16.01608638659267
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate size-induced distribution shifts in graphs and assess their impact on the ability of graph neural networks (GNNs) to generalize to larger graphs relative to the training data. Existing literature presents conflicting conclusions on GNNs' size generalizability, primarily due to disparities in application domains and underlying assumptions concerning size-induced distribution shifts. Motivated by this, we take a data-driven approach: we focus on real biological datasets and seek to characterize the types of size-induced distribution shifts. Diverging from prior approaches, we adopt a spectral perspective and identify that spectrum differences induced by size are related to differences in subgraph patterns (e.g., average cycle lengths). While previous studies have identified that the inability of GNNs in capturing subgraph information negatively impacts their in-distribution generalization, our findings further show that this decline is more pronounced when evaluating on larger test graphs not encountered during training. Based on these spectral insights, we introduce a simple yet effective model-agnostic strategy, which makes GNNs aware of these important subgraph patterns to enhance their size generalizability. Our empirical results reveal that our proposed size-insensitive attention strategy substantially enhances graph classification performance on large test graphs, which are 2-10 times larger than the training graphs, resulting in an improvement in F1 scores by up to 8%.

Related papers

• Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning [7.448831299106425]
  DISGEN is a model-agnostic framework designed to disentangle size factors from graph representations. Our empirical results show that DISGEN outperforms the state-of-the-art models by up to 6% on real-world datasets.
  arXiv  Detail & Related papers  (2024-06-07T03:19:24Z)
• Towards Causal Classification: A Comprehensive Study on Graph Neural Networks [9.360596957822471]
  Graph Neural Networks (GNNs) for processing graph-structured data have expanded their potential for causal analysis. Our study delves into nine benchmark graph classification models, testing their strength and versatility across seven datasets. Our findings are instrumental in furthering the understanding and practical application of GNNs in diverse datacentric fields.
  arXiv  Detail & Related papers  (2024-01-27T15:35:05Z)
• Learning to Reweight for Graph Neural Network [63.978102332612906]
  Graph Neural Networks (GNNs) show promising results for graph tasks. Existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data. We propose a novel nonlinear graph decorrelation method, which can substantially improve the out-of-distribution generalization ability.
  arXiv  Detail & Related papers  (2023-12-19T12:25:10Z)
• Graph Out-of-Distribution Generalization with Controllable Data Augmentation [51.17476258673232]
  Graph Neural Network (GNN) has demonstrated extraordinary performance in classifying graph properties. Due to the selection bias of training and testing data, distribution deviation is widespread. We propose OOD calibration to measure the distribution deviation of virtual samples.
  arXiv  Detail & Related papers  (2023-08-16T13:10:27Z)
• Addressing the Impact of Localized Training Data in Graph Neural Networks [0.0]
  Graph Neural Networks (GNNs) have achieved notable success in learning from graph-structured data. This article aims to assess the impact of training GNNs on localized subsets of the graph. We propose a regularization method to minimize distributional discrepancies between localized training data and graph inference.
  arXiv  Detail & Related papers  (2023-07-24T11:04:22Z)
• MentorGNN: Deriving Curriculum for Pre-Training GNNs [61.97574489259085]
  We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs. We shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs.
  arXiv  Detail & Related papers  (2022-08-21T15:12:08Z)
• 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)
• From Local Structures to Size Generalization in Graph Neural Networks [53.3202754533658]
  Graph neural networks (GNNs) can process graphs of different sizes. Their ability to generalize across sizes, specifically from small to large graphs, is still not well understood.
  arXiv  Detail & Related papers  (2020-10-17T19:36:54Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)

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.