Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learning

arXiv:2402.16374v1 Announce Type: new
Abstract: Graph learning plays a pivotal role and has gained significant attention in various application scenarios, from social network analysis to recommendation systems, for its effectiveness in modeling complex data relations represented by graph structural data. In reality, the real-world graph data typically show dynamics over time, with changing node attributes and edge structure, leading to the severe graph data distribution shift issue. This issue is compounded by the diverse and complex nature of distribution shifts, …

abstract analysis application arxiv attention continual cs.lg cs.si data distribution domain domain adaptation graph graph learning modeling network pivotal reality recommendation recommendation systems relations role social survey systems type world