Gradual Domain Adaptation for Graph Learning

2025-01-29

AI Summary

Graph data often exhibits significant distribution shifts across domains, and existing graph domain adaptation methods suffer from limited generalization capability. Method: This paper proposes a progressive graph domain adaptation framework. Contribution/Results: (1) It introduces a graph domain evolution mechanism based on vertex selection and adaptive progression to construct compact, information-preserving intermediate domains; (2) It pioneers the use of Fused Gromov–Wasserstein (FGW) distance with computable upper and lower bounds, enabling theoretical characterization and tractable optimization of otherwise intractable inter-domain distances; (3) It integrates knowledge-preserving intermediate graph generation with vertex-level domain progression to enable progressive fine-tuning of GNNs. Extensive experiments demonstrate that the method consistently outperforms state-of-the-art approaches on diverse large-shift cross-domain graph learning tasks, validating its robustness and effective transferability.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

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
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Existing literature lacks a graph domain adaptation technique for handling large distribution shifts, primarily due to the difficulty in simulating an evolving path from source to target graph. To make a breakthrough, we present a graph gradual domain adaptation (GGDA) framework with the construction of a compact domain sequence that minimizes information loss in adaptations. Our approach starts with an efficient generation of knowledge-preserving intermediate graphs over the Fused Gromov-Wasserstein (FGW) metric. With the bridging data pool, GGDA domains are then constructed via a novel vertex-based domain progression, which comprises"close"vertex selections and adaptive domain advancement to enhance inter-domain information transferability. Theoretically, our framework concretizes the intractable inter-domain distance $W_p(mu_t,mu_{t+1})$ via implementable upper and lower bounds, enabling flexible adjustments of this metric for optimizing domain formation. Extensive experiments under various transfer scenarios validate the superior performance of our GGDA framework.

Problem

• Graph Learning
• Domain Adaptation
• Variability in Graph Data

Innovation

• GGDA
• Fused Gromov-Wasserstein
• Graph Domain Adaptation