Graph Classification via Reference Distribution Learning: Theory and Practice

• URL: http://arxiv.org/abs/2408.11370v1
• Date: Wed, 21 Aug 2024 06:42:22 GMT
• Title: Graph Classification via Reference Distribution Learning: Theory and Practice
• Authors: Zixiao Wang, Jicong Fan,
• Abstract summary: This work introduces Graph Reference Distribution Learning (GRDL), an efficient and accurate graph classification method. GRDL treats each graph's latent node embeddings given by GNN layers as a discrete distribution, enabling direct classification without global pooling. Experiments on moderate-scale and large-scale graph datasets show the superiority of GRDL over the state-of-the-art.
• Score: 24.74871206083017
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph classification is a challenging problem owing to the difficulty in quantifying the similarity between graphs or representing graphs as vectors, though there have been a few methods using graph kernels or graph neural networks (GNNs). Graph kernels often suffer from computational costs and manual feature engineering, while GNNs commonly utilize global pooling operations, risking the loss of structural or semantic information. This work introduces Graph Reference Distribution Learning (GRDL), an efficient and accurate graph classification method. GRDL treats each graph's latent node embeddings given by GNN layers as a discrete distribution, enabling direct classification without global pooling, based on maximum mean discrepancy to adaptively learned reference distributions. To fully understand this new model (the existing theories do not apply) and guide its configuration (e.g., network architecture, references' sizes, number, and regularization) for practical use, we derive generalization error bounds for GRDL and verify them numerically. More importantly, our theoretical and numerical results both show that GRDL has a stronger generalization ability than GNNs with global pooling operations. Experiments on moderate-scale and large-scale graph datasets show the superiority of GRDL over the state-of-the-art, emphasizing its remarkable efficiency, being at least 10 times faster than leading competitors in both training and inference stages.

Related papers

• 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)
• GraphLoRA: Structure-Aware Contrastive Low-Rank Adaptation for Cross-Graph Transfer Learning [17.85404473268992]
  Graph Neural Networks (GNNs) have demonstrated remarkable proficiency in handling a range of graph analytical tasks. Despite their versatility, GNNs face significant challenges in transferability, limiting their utility in real-world applications. We propose GraphLoRA, an effective and parameter-efficient method for transferring well-trained GNNs to diverse graph domains.
  arXiv  Detail & Related papers  (2024-09-25T06:57:42Z)
• 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)
• 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)
• A Class-Aware Representation Refinement Framework for Graph Classification [8.998543739618077]
  We propose a Class-Aware Representation rEfinement (CARE) framework for the task of graph classification. CARE computes simple yet powerful class representations and injects them to steer the learning of graph representations towards better class separability. Our experiments with 11 well-known GNN backbones on 9 benchmark datasets validate the superiority and effectiveness of CARE over its GNN counterparts.
  arXiv  Detail & Related papers  (2022-09-02T10:18:33Z)
• 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)
• Graph Classification by Mixture of Diverse Experts [67.33716357951235]
  We present GraphDIVE, a framework leveraging mixture of diverse experts for imbalanced graph classification. With a divide-and-conquer principle, GraphDIVE employs a gating network to partition an imbalanced graph dataset into several subsets. Experiments on real-world imbalanced graph datasets demonstrate the effectiveness of GraphDIVE.
  arXiv  Detail & Related papers  (2021-03-29T14:03:03Z)
• 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)

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.