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 2107.01475cs.LGcs.CR
收藏

图的隐私保护表示学习:互信息视角

Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective

Illinois Institute of Technology(伊利诺伊理工学院);Duke University(杜克大学);Tsinghua University(清华大学)

Binghui Wang, Jiayi Guo, Ang Li, Yiran Chen, Hai Li

摘要:

图学习最近引起了人们的极大关注。现有的图上的表示学习方法已经取得了国家的最先进的性能在各种图形相关的任务,如节点分类,链接预测等,但是,我们观察到,这些方法可能会泄漏严重的私人信息。例如,可以从通过现有方法在学习的节点表示上训练的节点分类器(或链路预测器)准确地推断图中的链路(或节点标识)。为了解决这个问题,我们提出了一个隐私保护的表示学习框架图从\emph{mutual information}的角度来看。具体来说,我们的框架包括一个主要的学习任务和一个隐私保护任务,我们认为节点分类和链接预测作为感兴趣的两个任务。我们的目标是学习节点表示,使它们可以用于实现高性能的主要学习任务,同时获得性能接近随机猜测的隐私保护任务。我们通过互信息目标来正式制定我们的目标。然而,在实际中计算互信息是困难的。然后,我们推导出易于处理的变分界的互信息条款,每个边界可以通过一个神经网络参数化。接下来,我们训练这些参数化神经网络来近似真实的互信息,并学习隐私保护节点表示。最后,我们在各种图形数据集上评估我们的框架。

英文摘要:

Learning with graphs has attracted significant attention recently. Existing representation learning methods on graphs have achieved state-of-the-art performance on various graph-related tasks such as node classification, link prediction, etc. However, we observe that these methods could leak serious private information. For instance, one can accurately infer the links (or node identity) in a graph from a node classifier (or link predictor) trained on the learnt node representations by existing methods. To address the issue, we propose a privacy-preserving representation learning framework on graphs from the \emph{mutual information} perspective. Specifically, our framework includes a primary learning task and a privacy protection task, and we consider node classification and link prediction as the two tasks of interest. Our goal is to learn node representations such that they can be used to achieve high performance for the primary learning task, while obtaining performance for the privacy protection task close to random guessing. We formally formulate our goal via mutual information objectives. However, it is intractable to compute mutual information in practice. Then, we derive tractable variational bounds for the mutual information terms, where each bound can be parameterized via a neural network. Next, we train these parameterized neural networks to approximate the true mutual information and learn privacy-preserving node representations. We finally evaluate our framework on various graph datasets.

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。

↑