This paper addresses the challenge of out-of-distribution (OOD) generalization in graph machine learning, a field rapidly advancing yet grappling with the discrepancy between source and target data distributions. Traditional graph learning algorithms, based on the assumption of uniform distribution between training and test data, falter in real-world scenarios where this assumption fails, resulting in suboptimal performance. A principal factor contributing to this suboptimal performance is the inherent simplicity bias of neural networks trained through Stochastic Gradient Descent (SGD), which prefer simpler features over more complex yet equally or more predictive ones. This bias leads to a reliance on spurious correlations, adversely affecting OOD performance in various tasks such as image recognition, natural language understanding, and graph classification. Current methodologies, including subgraph-mixup and information bottleneck approaches, have achieved partial success but struggle to overcome simplicity bias, often reinforcing spurious correlations. To tackle this, we propose DIVE, training a collection of models to focus on all label-predictive subgraphs by encouraging the models to foster divergence on the subgraph mask, which circumvents the limitation of a model solely focusing on the subgraph corresponding to simple structural patterns. Specifically, we employs a regularizer to punish overlap in extracted subgraphs across models, thereby encouraging different models to concentrate on distinct structural patterns. Model selection for robust OOD performance is achieved through validation accuracy. Tested across four datasets from GOOD benchmark and one dataset from DrugOOD benchmark, our approach demonstrates significant improvement over existing methods, effectively addressing the simplicity bias and enhancing generalization in graph machine learning.
Diversify & Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement
Seoul National University（首尔大学）；Automation and Systems Research Institute (ASRI)（自动化与系统研究所）；Artificial Intelligence Institute of Seoul National University (AIIS)（首尔大学人工智能研究所）
Towards Effective Graph Rationalization via Boosting Environment Diversity
School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）；School of Computer and Information Technology, Shanxi University（山西大学计算机与信息技术学院）
Finding Diverse and Predictable Subgraphs for Graph Domain Generalization
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
Computer Science Technion - Israel Institute of Technology（技术学院-以色列理工学院计算机科学系）；Electrical & Computer Engineering Technion - Israel Institute of Technology（技术学院-以色列理工学院电气与计算机工程系）；NVIDIA Research（NVIDIA研究）
Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
Texas A&M University（德州农工大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Georgia（佐治亚大学）；Rice University（莱斯大学）；Samsung Electronics America（三星电子美国公司）；Samsung Electronics（三星电子）
Unlearning on Spatio-Temporal Graphs through Subgraph Virtual Edge Reconstruction
Texas A&M University - Corpus Christi（德州农工大学科珀斯克里斯蒂分校）；Delft University of Technology（代尔夫特理工大学）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；Biogen（渤健公司）
