Out-of-Distribution Generalization on Graphs via Progressive Inference

GPro improves graph out-of-distribution generalization by decomposing causal invariant learning into progressive inference steps and augmenting training with counterfactual samples, outperforming state-of-the-art methods by 4.91%.

Yiming Xu, Bin Shi, Zhen Peng, Huixiang Liu, Bo Dong, Chen Chen

Published Apr 11, 20253 citationsPaper ↗

74%

OverallHighly rated

OverallHighly ratedVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel9/20reviewers recommend it

lenient 4/5

medium 5/10

strict 0/5

AI panel?Vote to see what the 20 AI reviewers said

Panel consensus

GPro delivers a measurable 4.91% out-of-distribution gain and valuable diagnostic steps toward ground-truth causal parts, yet its progressive inference may mask weak selection, counterfactual augmentation risks synthetic bias, and implementation details remain unverified.

Abstract

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation mechanism. In particular, when the data distribution shows a significant shift, most GNNs would fail to produce reliable predictions and may even make decisions randomly. One of the most promising solutions to improve the model generalization is to pick out causal invariant parts in the input graph. Nonetheless, we observe a significant distribution gap between the causal parts learned by existing methods and the ground-truth, leading to undesirable performance. In response to the above issues, this paper presents GPro, a model that learns graph causal invariance with progressive inference. Specifically, the complicated graph causal invariant learning is decomposed into multiple intermediate inference steps from easy to hard, and the perception of GPro is continuously strengthened through a progressive inference process to extract causal features that are stable to distribution shifts. We also enlarge the training distribution by creating counterfactual samples to enhance the capability of the GPro in capturing the causal invariant parts. Extensive experiments demonstrate that our proposed GPro outperforms the state-of-the-art methods by 4.91% on average. For datasets with more severe distribution shifts, the performance improvement can be up to 6.86%.