Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation

TL;DR

This paper introduces DiffGDA, a diffusion-based method for graph domain adaptation that models continuous structural and semantic evolution, outperforming fixed-step approaches in real-world scenarios.

Contribution

It proposes a novel diffusion process using stochastic differential equations to model continuous graph evolution for domain adaptation, guided by a domain-aware network.

Findings

Outperforms state-of-the-art baselines on 14 graph transfer tasks

Models continuous structural and semantic evolution effectively

Theoretically converges to optimal domain bridging solution

Abstract

Graph Domain Adaptation (GDA) aims to bridge distribution shifts between domains by transferring knowledge from well-labeled source graphs to given unlabeled target graphs. One promising recent approach addresses graph transfer by discretizing the adaptation process, typically through the construction of intermediate graphs or stepwise alignment procedures. However, such discrete strategies often fail in real-world scenarios, where graph structures evolve continuously and nonlinearly, making it difficult for fixed-step alignment to approximate the actual transformation process. To address these limitations, we propose \textbf{DiffGDA}, a \textbf{Diff}usion-based \textbf{GDA} method that models the domain adaptation process as a continuous-time generative process. We formulate the evolution from source to target graphs using stochastic differential equations (SDEs), enabling the joint modeling of structural and semantic transitions. To guide this evolution, a domain-aware network is introduced to steer the generative process toward the target domain, encouraging the diffusion trajectory to follow an optimal adaptation path. We theoretically show that the diffusion process converges to the optimal solution bridging the source and target domains in the latent space. Extensive experiments on 14 graph transfer tasks across 8 real-world datasets demonstrate DiffGDA consistently outperforms state-of-the-art baselines.