Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization
- URL: http://arxiv.org/abs/2306.08076v2
- Date: Wed, 5 Jun 2024 01:41:31 GMT
- Title: Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization
- Authors: Xiner Li, Shurui Gui, Youzhi Luo, Shuiwang Ji,
- Abstract summary: 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.
- Score: 54.64375566326931
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Out-of-distribution (OOD) generalization deals with the prevalent learning scenario where test distribution shifts from training distribution. With rising application demands and inherent complexity, graph OOD problems call for specialized solutions. While data-centric methods exhibit performance enhancements on many generic machine learning tasks, there is a notable absence of data augmentation methods tailored for graph OOD generalization. In this work, we propose to achieve graph OOD generalization with the novel design of non-Euclidean-space linear extrapolation. The proposed augmentation strategy extrapolates both structure and feature spaces to generate OOD graph data. Our design tailors OOD samples for specific shifts without corrupting underlying causal mechanisms. Theoretical analysis and empirical results evidence the effectiveness of our method in solving target shifts, showing substantial and constant improvements across various graph OOD tasks.
Related papers
- Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on
Graphs [22.561747395557642]
We provide an up-to-date and forward-looking review of graph Out-Of-Distribution (OOD) adaptation methods.
Based on our proposed taxonomy for graph OOD adaptation, we systematically categorize the existing methods according to their learning paradigm.
We point out promising research directions and the corresponding challenges.
arXiv Detail & Related papers (2024-02-17T00:40:12Z) - Unifying Invariance and Spuriousity for Graph Out-of-Distribution via
Probability of Necessity and Sufficiency [19.49531172542614]
We propose a unified framework to exploit the Probability of Necessity and Sufficiency to extract the Invariant Substructure (PNSIS)
Our model outperforms the state-of-the-art techniques on graph OOD on several benchmarks.
arXiv Detail & Related papers (2024-02-14T13:31:53Z) - Investigating Out-of-Distribution Generalization of GNNs: An
Architecture Perspective [45.352741792795186]
We show that the graph self-attention mechanism and the decoupled architecture contribute positively to graph OOD generalization.
We develop a novel GNN backbone model, DGAT, designed to harness the robust properties of both graph self-attention mechanism and the decoupled architecture.
arXiv Detail & Related papers (2024-02-13T05:38:45Z) - Joint Learning of Label and Environment Causal Independence for Graph
Out-of-Distribution Generalization [60.4169201192582]
We propose to incorporate label and environment causal independence (LECI) to fully make use of label and environment information.
LECI significantly outperforms prior methods on both synthetic and real-world datasets.
arXiv Detail & Related papers (2023-06-01T19:33:30Z) - GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection [67.90365841083951]
We develop a new graph contrastive learning framework GOOD-D for detecting OOD graphs without using any ground-truth labels.
GOOD-D is able to capture the latent ID patterns and accurately detect OOD graphs based on the semantic inconsistency in different granularities.
As a pioneering work in unsupervised graph-level OOD detection, we build a comprehensive benchmark to compare our proposed approach with different state-of-the-art methods.
arXiv Detail & Related papers (2022-11-08T12:41:58Z) - 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 [77.14319095965058]
We formulate the OOD problem for node-level prediction on graphs.
We develop a new domain-invariant learning approach, named Explore-to-Extrapolate Risk Minimization.
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.