2022/06/19 by Junchi Yu, Jian Liang, Yu, Junchi +3 · 1 citation
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2206.09345
openalex publication_date 2022/06/19 · openalex created_date 2022/06/24 · openalex updated_date 2026/07/28
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 Diverse and Predictable Subgraphs 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 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.