Finding Diverse and Predictable Subgraphs for Graph Domain Generalization

TL;DR

This paper introduces DPS, a novel framework that constructs multiple diverse and predictable subgraphs from source domains to improve out-of-distribution generalization in graph neural networks, especially when source domains are limited.

Contribution

DPS is a new framework that generates multiple subgraphs to enhance domain generalization without requiring many source domains, adaptable to various GNN architectures.

Findings

DPS outperforms existing methods on node-level benchmarks.

DPS achieves significant improvements on graph-level tasks.

The framework is model-agnostic and effective across different GNN backbones.

Abstract

This paper focuses on out-of-distribution generalization on graphs where performance drops due to the unseen distribution shift. Previous graph domain generalization works always resort to learning an invariant predictor among different source domains. However, they assume sufficient source domains are available during training, posing huge challenges for realistic applications. By contrast, we propose a new graph domain generalization framework, dubbed as DPS, by constructing multiple populations from the source domains. Specifically, DPS aims to discover multiple \textbf{D}iverse and \textbf{P}redictable \textbf{S}ubgraphs with a set of generators, namely, subgraphs are different from each other but all the them share the same semantics with the input graph. These generated source domains are exploited to learn an \textit{equi-predictive} graph neural network (GNN) across domains, which is expected to generalize well to unseen target domains. Generally, DPS is model-agnostic that can be incorporated with various GNN backbones. Extensive experiments on both node-level and graph-level benchmarks shows that the proposed DPS achieves impressive performance for various graph domain generalization tasks.