SA-GDA: Spectral Augmentation for Graph Domain Adaptation

2023-10-26

ACM Multimedia

AI Summary

To address label scarcity and cross-domain feature confusion in unsupervised domain adaptation for graph node classification, this paper proposes a spectral-domain, class-level feature alignment method. Specifically, it explicitly aligns representations of nodes from the same class across source and target domains in the Laplacian spectral domain—thereby avoiding category confusion induced by holistic feature alignment. We theoretically establish its spectral stability under domain shift. A dual graph convolutional architecture is designed to jointly preserve local and global consistency, while an adversarial domain classifier facilitates knowledge transfer. This work is the first to introduce class-aware alignment into spectral-domain graph domain adaptation. Extensive experiments on multiple public benchmarks demonstrate significant improvements over state-of-the-art methods, achieving absolute accuracy gains of 5.2–9.7% on target domains with low label rates.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness
• 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
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Graph neural networks (GNNs) have achieved impressive impressions for graph-related tasks. However, most GNNs are primarily studied under the cases of signal domain with supervised training, which requires abundant task-specific labels and is difficult to transfer to other domains. There are few works focused on domain adaptation for graph node classification. They mainly focused on aligning the feature space of the source and target domains, without considering the feature alignment between different categories, which may lead to confusion of classification in the target domain. However, due to the scarcity of labels of the target domain, we cannot directly perform effective alignment of categories from different domains, which makes the problem more challenging. In this paper, we present the Spectral Augmentation for Graph Domain Adaptation (SA-GDA) for graph node classification. First, we observe that nodes with the same category in different domains exhibit similar characteristics in the spectral domain, while different classes are quite different. Following the observation, we align the category feature space of different domains in the spectral domain instead of aligning the whole features space, and we theoretical proof the stability of proposed SA-GDA. Then, we develop a dual graph convolutional network to jointly exploits local and global consistency for feature aggregation. Last, we utilize a domain classifier with an adversarial learning submodule to facilitate knowledge transfer between different domain graphs. Experimental results on a variety of publicly available datasets reveal the effectiveness of our SA-GDA.

Problem

• Addresses domain adaptation for graph node classification
• Aligns category feature space in spectral domain
• Utilizes adversarial learning for knowledge transfer

Innovation

• Aligns category feature space in spectral domain
• Uses dual graph convolutional network
• Employs adversarial domain classifier