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 2502.06808cs.LGcs.AI
收藏

论属性驱动图域自适应的优势

On the Benefits of Attribute-Driven Graph Domain Adaptation

Western University(西安大略大学);Michigan State University(密歇根州立大学);Vector Institute(向量研究所);University of Electronic Science and Technology of China(电子科技大学)

Ruiyi Fang, Bingheng Li, Zhao Kang, Qiuhao Zeng, Nima Hosseini Dashtbayaz, Ruizhi Pu, Boyu Wang, Charles Ling

AI总结:

本文通过理论和实验证明节点属性偏移在图域自适应中比结构偏移更关键,并提出跨通道模块融合对齐源图与目标图的属性与结构视图,提升跨网络学习性能。

摘要:

图域自适应(GDA)解决了跨网络学习中的一个紧迫挑战,尤其是在现实世界图数据集中缺乏标注数据的情况下显得尤为重要。近期研究试图通过消除图之间的结构偏移来学习域不变表示。在本工作中,我们表明现有方法忽视了图节点属性的重要性,而节点属性是图域对齐的关键因素。具体而言,我们首先通过理论证明揭示了节点属性对GDA的影响,表明除了域之间的图结构差异外,节点属性差异在GDA中也起着关键作用。此外,我们还通过实验表明,属性偏移比拓扑偏移更为显著,这进一步强调了在GDA中节点属性对齐的重要性。受此发现启发,我们开发了一种新颖的跨通道模块,用于融合并对齐源图与目标图之间的两种视图,以实现GDA。在多个基准上的实验结果验证了我们方法的有效性。

英文摘要:

Graph Domain Adaptation (GDA) addresses a pressing challenge in cross-network learning, particularly pertinent due to the absence of labeled data in real-world graph datasets. Recent studies attempted to learn domain invariant representations by eliminating structural shifts between graphs. In this work, we show that existing methodologies have overlooked the significance of the graph node attribute, a pivotal factor for graph domain alignment. Specifically, we first reveal the impact of node attributes for GDA by theoretically proving that in addition to the graph structural divergence between the domains, the node attribute discrepancy also plays a critical role in GDA. Moreover, we also empirically show that the attribute shift is more substantial than the topology shift, which further underscores the importance of node attribute alignment in GDA. Inspired by this finding, a novel cross-channel module is developed to fuse and align both views between the source and target graphs for GDA. Experimental results on a variety of benchmarks verify 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。

↑