Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective

• URL: http://arxiv.org/abs/2505.05785v1
• Date: Fri, 09 May 2025 04:58:48 GMT
• Title: Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective
• Authors: Henan Sun, Xunkai Li, Lei Zhu, Junyi Han, Guang Zeng, Ronghua Li, Guoren Wang,
• Abstract summary: Out-Of-Distribution (OOD) generalization has gained increasing attentions for machine learning on graphs.<n>We propose learnable random walk (LRW) perspective as the instantiation of invariant knowledge.<n>Our model can effectively enhance graph OOD generalization under various types of distribution shifts and yield a significant accuracy improvement of 3.87%.
• Score: 29.59986993135573
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Out-Of-Distribution (OOD) generalization has gained increasing attentions for machine learning on graphs, as graph neural networks (GNNs) often exhibit performance degradation under distribution shifts. Existing graph OOD methods tend to follow the basic ideas of invariant risk minimization and structural causal models, interpreting the invariant knowledge across datasets under various distribution shifts as graph topology or graph spectrum. However, these interpretations may be inconsistent with real-world scenarios, as neither invariant topology nor spectrum is assured. In this paper, we advocate the learnable random walk (LRW) perspective as the instantiation of invariant knowledge, and propose LRW-OOD to realize graph OOD generalization learning. Instead of employing fixed probability transition matrix (i.e., degree-normalized adjacency matrix), we parameterize the transition matrix with an LRW-sampler and a path encoder. Furthermore, we propose the kernel density estimation (KDE)-based mutual information (MI) loss to generate random walk sequences that adhere to OOD principles. Extensive experiment demonstrates that our model can effectively enhance graph OOD generalization under various types of distribution shifts and yield a significant accuracy improvement of 3.87% over state-of-the-art graph OOD generalization baselines.

Related papers

• Generative Risk Minimization for Out-of-Distribution Generalization on Graphs [71.48583448654522]
  We propose an innovative framework, named Generative Risk Minimization (GRM), designed to generate an invariant subgraph for each input graph to be classified, instead of extraction.<n>We conduct extensive experiments across a variety of real-world graph datasets for both node-level and graph-level OOD generalization.
  arXiv  Detail & Related papers  (2025-02-11T21:24:13Z)
• Subgraph Aggregation for Out-of-Distribution Generalization on Graphs [29.884717215947745]
  SubGraph Aggregation (SuGAr) is designed to learn a diverse set of subgraphs that are crucial for OOD generalization on graphs.<n>Experiments on both synthetic and real-world datasets demonstrate that SuGAr outperforms state-of-the-art methods, achieving up to a 24% improvement in OOD generalization on graphs.
  arXiv  Detail & Related papers  (2024-10-29T16:54:37Z)
• A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation [59.14165404728197]
  We provide an up-to-date and forward-looking review of deep graph learning under distribution shifts.<n>Specifically, we cover three primary scenarios: graph OOD generalization, training-time graph OOD adaptation, and test-time graph OOD adaptation.<n>To provide a better understanding of the literature, we introduce a systematic taxonomy that classifies existing methods into model-centric and data-centric approaches.
  arXiv  Detail & Related papers  (2024-10-25T02:39:56Z)
• Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalization [9.116601683256317]
  In this work, we propose a novel framework, called Invariant Graph Learning based on Information bottleneck theory (InfoIGL)<n>Specifically, InfoIGL introduces a redundancy filter to compress task-irrelevant information related to environmental factors.<n>Experiments on both synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance under OOD generalization.
  arXiv  Detail & Related papers  (2024-08-03T07:38:04Z)
• Graph Out-of-Distribution Generalization via Causal Intervention [69.70137479660113]
  We introduce a conceptually simple yet principled approach for training robust graph neural networks (GNNs) under node-level distribution shifts. Our method resorts to a new learning objective derived from causal inference that coordinates an environment estimator and a mixture-of-expert GNN predictor. Our model can effectively enhance generalization with various types of distribution shifts and yield up to 27.4% accuracy improvement over state-of-the-arts on graph OOD generalization benchmarks.
  arXiv  Detail & Related papers  (2024-02-18T07:49:22Z)
• Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization [54.64375566326931]
  Out-of-distribution (OOD) generalization deals with the prevalent learning scenario where test distribution shifts from training distribution. We propose to achieve graph OOD generalization with the novel design of non-Euclidean-space linear extrapolation. Our design tailors OOD samples for specific shifts without corrupting underlying causal mechanisms.
  arXiv  Detail & Related papers  (2023-06-13T18:46:28Z)
• Invariance Principle Meets Out-of-Distribution Generalization on Graphs [66.04137805277632]
  Complex nature of graphs thwarts the adoption of the invariance principle for OOD generalization. domain or environment partitions, which are often required by OOD methods, can be expensive to obtain for graphs. We propose a novel framework to explicitly model this process using a contrastive strategy.
  arXiv  Detail & Related papers  (2022-02-11T04:38:39Z)
• Handling Distribution Shifts on Graphs: An Invariance Perspective [78.31180235269035]
  We formulate the OOD problem on graphs and develop a new invariant learning approach, Explore-to-Extrapolate Risk Minimization (EERM) EERM resorts to multiple context explorers that are adversarially trained to maximize the variance of risks from multiple virtual environments. We prove the validity of our method by theoretically showing its guarantee of a valid OOD solution.
  arXiv  Detail & Related papers  (2022-02-05T02:31:01Z)

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.