Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation

2026-02-11

AI Summary

This work addresses the challenge in graph domain adaptation where conventional discrete alignment strategies fail due to the continuous and nonlinear evolution of graph structures. To overcome this limitation, we introduce diffusion models into this domain for the first time and propose a continuous evolution modeling paradigm based on stochastic differential equations. Our approach jointly models the dynamic evolution of both graph structure and semantics and incorporates a domain-aware guidance network to steer the diffusion trajectory toward an optimal adaptation path. Extensive experiments across 14 graph transfer tasks on eight real-world datasets demonstrate that our method significantly outperforms current state-of-the-art approaches, confirming its effectiveness and strong generalization capability.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Diffusion Models for Vision
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Models for Web evolution

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.

Problem

• Graph Domain Adaptation
• continuous evolution
• structure-semantic trajectory
• distribution shift
• graph transfer

Innovation

• Graph Domain Adaptation
• Diffusion Model
• Stochastic Differential Equations
• Continuous-time Generative Process
• Structure-Semantic Evolution