arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.07482cs.LG
收藏

图领域自适应:一种生成的观点

Graph Domain Adaptation: A Generative View

Guangdong University of Technology(广东工业大学);National University of Singapore(新加坡国立大学);Tencent Technology (SZ) Co., Ltd.(腾讯科技(深圳)有限公司);Carnegie Mellon University(卡内基梅隆大学)

Ruichu Cai, Fengzhu Wu, Zijian Li, Pengfei Wei, Lingling Yi, Kun Zhang

摘要:

近年来,人们对图结构数据的深度学习产生了极大的兴趣。由于收集标记图结构数据的成本很高,领域自适应对于有限样本的有监督图学习任务很重要。然而,目前的图领域自适应方法通常是从传统的领域自适应任务中获得的,没有很好地利用图结构数据的特性。例如,在不同平台上观察到的社交网络不仅受不同人群或社区的控制,而且还受特定于域的策略和背景噪声的控制。基于图结构数据中的这些属性,我们首先假设图结构数据生成过程由三种独立类型的潜变量控制,即,语义潜变量、领域潜变量和随机潜变量。基于这一假设,我们提出了一种基于去纠缠的无监督领域自适应方法的图结构数据,该方法采用变分图自动编码器恢复这些潜在变量,并通过三个监督学习模块将它们去纠缠。在两个真实数据集上的实验结果表明,该方法不仅显著优于传统的领域自适应方法和基于解纠缠的领域自适应方法,而且优于最先进的图领域自适应算法.

英文摘要:

Recent years have witnessed tremendous interest in deep learning on graph-structured data. Due to the high cost of collecting labeled graph-structured data, domain adaptation is important to supervised graph learning tasks with limited samples. However, current graph domain adaptation methods are generally adopted from traditional domain adaptation tasks, and the properties of graph-structured data are not well utilized. For example, the observed social networks on different platforms are controlled not only by the different crowd or communities but also by the domain-specific policies and the background noise. Based on these properties in graph-structured data, we first assume that the graph-structured data generation process is controlled by three independent types of latent variables, i.e., the semantic latent variables, the domain latent variables, and the random latent variables. Based on this assumption, we propose a disentanglement-based unsupervised domain adaptation method for the graph-structured data, which applies variational graph auto-encoders to recover these latent variables and disentangles them via three supervised learning modules. Extensive experimental results on two real-world datasets in the graph classification task reveal that our method not only significantly outperforms the traditional domain adaptation methods and the disentangled-based domain adaptation methods but also outperforms the state-of-the-art graph domain adaptation algorithms.

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。

↑