Non-IID Transfer Learning on Graphs

TL;DR

This paper develops theoretical bounds and algorithms for transfer learning on non-IID graphs, introducing a novel measure of graph distribution shift and a graph adaptive network to improve cross-network tasks.

Contribution

It proposes a new theoretical framework and algorithms for non-IID transfer learning on graphs, including a graph discrepancy measure and a graph adaptive network (GRADE).

Findings

Effective transfer learning on non-IID graphs demonstrated.

The GRADE framework improves cross-network node classification.

Theoretical bounds relate transfer error to graph discrepancy.

Abstract

Transfer learning refers to the transfer of knowledge or information from a relevant source domain to a target domain. However, most existing transfer learning theories and algorithms focus on IID tasks, where the source/target samples are assumed to be independent and identically distributed. Very little effort is devoted to theoretically studying the knowledge transferability on non-IID tasks, e.g., cross-network mining. To bridge the gap, in this paper, we propose rigorous generalization bounds and algorithms for cross-network transfer learning from a source graph to a target graph. The crucial idea is to characterize the cross-network knowledge transferability from the perspective of the Weisfeiler-Lehman graph isomorphism test. To this end, we propose a novel Graph Subtree Discrepancy to measure the graph distribution shift between source and target graphs. Then the generalization error bounds on cross-network transfer learning, including both cross-network node classification and link prediction tasks, can be derived in terms of the source knowledge and the Graph Subtree Discrepancy across domains. This thereby motivates us to propose a generic graph adaptive network (GRADE) to minimize the distribution shift between source and target graphs for cross-network transfer learning. Experimental results verify the effectiveness and efficiency of our GRADE framework on both cross-network node classification and cross-domain recommendation tasks.