arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.01467cs.LGcs.AI
收藏

协作以适应:通过双向适应实现无源图域适应

Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation

National University of Singapore(新加坡国立大学);Zhejiang University(浙江大学);Alibaba Group(阿里巴巴集团);Zhejiang Lab(之江实验室);Hangzhou Yugu Technology Co., Ltd.(杭州玉谷科技有限公司)

Zhen Zhang, Meihan Liu, Anhui Wang, Hongyang Chen, Zhao Li, Jiajun Bu, Bingsheng He

AI总结:

针对无法访问有标签源图的无监督图域适应问题,提出 GraphCTA 范式,通过模型适应与图适应的双向协作循环提升目标图性能,并在多个数据集上显著优于无源基线。

摘要:

无监督图域适应(Unsupervised Graph Domain Adaptation,UGDA)已成为一种实用解决方案,可将知识从标签丰富的源图迁移到完全无标签的目标图。然而,大多数方法都需要有标签源图来提供监督信号,而在现实场景中,由于法规和隐私问题,这种源图可能无法获取。本文研究无源无监督图域适应场景,即在不访问有标签源图的情况下解决域适应问题。具体而言,我们提出了一种名为 GraphCTA 的新范式,通过一系列流程协作执行模型适应和图适应:(1)基于目标图中节点的邻域预测进行模型适应,同时考虑局部和全局信息;(2)通过邻域对比学习更新图结构和节点属性,从而执行图适应;(3)更新后的图作为输入,促进后续的模型适应迭代,从而在模型适应与图适应之间建立协作循环。我们在多个公共数据集上进行了全面实验。实验结果表明,所提出模型以大幅优势优于近期的无源基线方法。

英文摘要:

Unsupervised Graph Domain Adaptation (UGDA) has emerged as a practical solution to transfer knowledge from a label-rich source graph to a completely unlabelled target graph. However, most methods require a labelled source graph to provide supervision signals, which might not be accessible in the real-world settings due to regulations and privacy concerns. In this paper, we explore the scenario of source-free unsupervised graph domain adaptation, which tries to address the domain adaptation problem without accessing the labelled source graph. Specifically, we present a novel paradigm called GraphCTA, which performs model adaptation and graph adaptation collaboratively through a series of procedures: (1) conduct model adaptation based on node's neighborhood predictions in target graph considering both local and global information; (2) perform graph adaptation by updating graph structure and node attributes via neighborhood contrastive learning; and (3) the updated graph serves as an input to facilitate the subsequent iteration of model adaptation, thereby establishing a collaborative loop between model adaptation and graph adaptation. Comprehensive experiments are conducted on various public datasets. The experimental results demonstrate that our proposed model outperforms recent source-free baselines by large margins.

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。

↑