arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.09189cs.LGcs.AI
收藏

SA-GDA:用于图领域适应的谱增强

SA-GDA: Spectral Augmentation for Graph Domain Adaptation

Beijing Institute of Technology(北京理工大学);Michigan State University(密歇根州立大学);California State Polytechnic University, Pomona(加州州立大学,庞纳);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Jinhui Pang, Zixuan Wang, Jiliang Tang, Mingyan Xiao, Nan Yin

AI总结:

针对图节点分类的领域适应问题,提出SA-GDA方法,通过在谱域中对齐类别特征空间并利用双图卷积网络和对抗学习,有效促进了跨域知识转移并提升了分类性能。

摘要:

图神经网络(GNNs)在图相关任务中取得了令人瞩目的成果。然而,大多数GNN主要在信号域的监督训练情况下进行研究,这需要大量特定任务的标签,并且难以迁移到其他领域。目前很少有工作关注图节点分类的领域适应。这些工作主要集中于对齐源域和目标域的特征空间,而没有考虑不同类别之间的特征对齐,这可能导致目标域中的分类混淆。然而,由于目标域标签的稀缺性,我们无法直接对不同域的类别进行有效对齐,这使得问题更具挑战性。在本文中,我们提出了用于图节点分类的谱增强图领域适应(SA-GDA)。首先,我们观察到不同域中相同类别的节点在谱域中表现出相似的特征,而不同类别则差异很大。基于这一观察,我们在谱域中对齐不同域的类别特征空间,而不是对齐整个特征空间,并且我们从理论上证明了所提出的SA-GDA的稳定性。然后,我们开发了一个双图卷积网络,以联合利用局部和全局一致性进行特征聚合。最后,我们利用带有对抗学习子模块的域分类器来促进不同域图之间的知识转移。在多种公开可用数据集上的实验结果证明了我们的SA-GDA的有效性。

英文摘要:

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 \textit{Spectral Augmentation for Graph Domain Adaptation (\method{})} 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 \method{}. 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 \method{}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑