Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics

TL;DR

This paper introduces Gadget, a novel graph domain adaptation framework that leverages Fused Gromov-Wasserstein geodesics to handle large distribution shifts in non-IID graph data, improving accuracy significantly.

Contribution

Gadget is the first GDA framework for non-IID graphs using FGW distance and geodesics, providing theoretical error bounds and an efficient path generation algorithm.

Findings

Improves graph DA accuracy by up to 6.8% on real datasets.

Derives error bounds showing target error proportional to path length.

Identifies FGW geodesic as the optimal adaptation path.

Abstract

Graph neural networks, despite their impressive performance, are highly vulnerable to distribution shifts on graphs. Existing graph domain adaptation (graph DA) methods often implicitly assume a mild shift between source and target graphs, limiting their applicability to real-world scenarios with large shifts. Gradual domain adaptation (GDA) has emerged as a promising approach for addressing large shifts by gradually adapting the source model to the target domain via a path of unlabeled intermediate domains. Existing GDA methods exclusively focus on independent and identically distributed (IID) data with a predefined path, leaving their extension to non-IID graphs without a given path an open challenge. To bridge this gap, we present Gadget, the first GDA framework for non-IID graph data. First (theoretical foundation), the Fused Gromov-Wasserstein (FGW) distance is adopted as the domain discrepancy for non-IID graphs, based on which, we derive an error bound on node, edge and graph-level tasks, showing that the target domain error is proportional to the length of the path. Second (optimal path), guided by the error bound, we identify the FGW geodesic as the optimal path, which can be efficiently generated by our proposed algorithm. The generated path can be seamlessly integrated with existing graph DA methods to handle large shifts on graphs, improving state-of-the-art graph DA methods by up to 6.8% in accuracy on real-world datasets.