GI-Graph: A Generative Invariant Graph Learning Scheme Towards Out-of-Distribution Generalization

When distribution shifts occur between testing and training graph data, out-of-distribution (OOD) samples undermine the performance of graph neural networks (GNNs). To improve adaptive OOD generalization of GNNs, this paper introduces a novel generative invariant graph learning framework, named GI-Graph. It consists of four modules: subgraph extractor, generative environment subgraph augmentation, generative invariant subgraph learning, and query feedback module. The subgraph extractor decomposes a graph sample into an environment subgraph and an invariant subgraph and improves extraction accuracy through query feedback. GI-Graph uses a diffusion model to generate diverse environment subgraphs, augmenting the OOD data. By combining diffusion models, contrastive learning, and attribute prediction networks, GI-Graph also generates augmented invariant subgraphs with significant identically distributed features and consistency of labels. Experimental results demonstrate that the controllable environment subgraph and invariant subgraph augmentation effectively improve the OOD generalization capability of GI-Graph, especially in capturing invariant features and maintaining category consistency across environments. Additionally, the contrastive learning-based finetuning method enables GI-Graph to quickly adapt to evolving environments. This paper verifies the effectiveness of the generative invariant graph learning scheme in graph OOD generalization.