Augmenting Knowledge Transfer across Graphs

TL;DR

This paper introduces TRANSNET, a novel framework that enhances knowledge transfer across graphs by using a trinity signal concept and a domain unification approach, significantly improving performance on benchmark datasets.

Contribution

The paper proposes a new trinity signal formulation and a domain unification module with mixup scheme to better transfer knowledge across graphs, addressing limitations of existing domain discrepancy methods.

Findings

Outperforms existing methods on seven benchmark datasets

Effectively reduces domain discrepancy and improves generalization

Demonstrates robustness across diverse graph structures

Abstract

Given a resource-rich source graph and a resource-scarce target graph, how can we effectively transfer knowledge across graphs and ensure a good generalization performance? In many high-impact domains (e.g., brain networks and molecular graphs), collecting and annotating data is prohibitively expensive and time-consuming, which makes domain adaptation an attractive option to alleviate the label scarcity issue. In light of this, the state-of-the-art methods focus on deriving domain-invariant graph representation that minimizes the domain discrepancy. However, it has recently been shown that a small domain discrepancy loss may not always guarantee a good generalization performance, especially in the presence of disparate graph structures and label distribution shifts. In this paper, we present TRANSNET, a generic learning framework for augmenting knowledge transfer across graphs. In particular, we introduce a novel notion named trinity signal that can naturally formulate various graph signals at different granularity (e.g., node attributes, edges, and subgraphs). With that, we further propose a domain unification module together with a trinity-signal mixup scheme to jointly minimize the domain discrepancy and augment the knowledge transfer across graphs. Finally, comprehensive empirical results show that TRANSNET outperforms all existing approaches on seven benchmark datasets by a significant margin.