Graph Domain Adaptation: Challenges, Progress and Prospects

TL;DR

This paper provides the first comprehensive survey of graph domain adaptation, discussing its challenges, recent advances, and future prospects in transfer learning for graph-structured data.

Contribution

It offers a detailed taxonomy, reviews representative works, and highlights research challenges and future directions in graph domain adaptation.

Findings

Identifies key challenges in GDA

Classifies GDA methods into a taxonomy

Discusses future research prospects

Abstract

As graph representation learning often suffers from label scarcity problems in real-world applications, researchers have proposed graph domain adaptation (GDA) as an effective knowledge-transfer paradigm across graphs. In particular, to enhance model performance on target graphs with specific tasks, GDA introduces a bunch of task-related graphs as source graphs and adapts the knowledge learnt from source graphs to the target graphs. Since GDA combines the advantages of graph representation learning and domain adaptation, it has become a promising direction of transfer learning on graphs and has attracted an increasing amount of research interest in recent years. In this paper, we comprehensively overview the studies of GDA and present a detailed survey of recent advances. Specifically, we outline the research status and challenges, propose a taxonomy, introduce the details of representative works, and discuss the prospects. To the best of our knowledge, this paper is the first survey for graph domain adaptation. A detailed paper list is available at https://github.com/Skyorca/Awesome-Graph-Domain-Adaptation-Papers.