In recent years, edge computing (EC) has attracted great attention for its high-speed computing and low-latency characteristics. However, there are many challenges in the implementation of EC. Firstly, user's privacy has been raised as a major concern because the edge devices may be untrustworthy. In the case of Private Edge Computing (PEC), a user wants to compute a matrix multiplication between its local matrix and one of the matrices in a library, which has been redundantly stored in edge devices. When utilizing resources of edge devices, the privacy requires that each edge device cannot know which matrix stored on it is desired by the user for the multiplication. Secondly, edge devices usually have limited communication and storage resources, which makes it impossible for them to store all matrices in the library. In this paper, we consider the limited resources of edge devices and propose an unified framework for PEC. Within the framework, we study two highly-coupled problems, (1) storage allocation, that determines which matrices are stored on each edge device, and (2) computation design, that determines which matrices (or linear combinations of them) in each edge device are selected to participate in the computing process with the privacy consideration. Specifically, we give a general storage allocation scheme and then design two feasible private computation schemes, i.e., General Private Computation (GPC) scheme and Private Coded Computation (PCC) scheme. In particular, GPC can be applied in general case and PCC can only be applied in special cases, while PCC achieves less communication load. We theoretically analyze the proposed computing schemes and compare them with other schemes. Finally, we conduct extensive simulations to show the effectiveness of the proposed schemes.
BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation
School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);Guangdong Key Laboratory of Big Data Analysis and Processing(广东大数据分析与处理重点实验室);Department of Computing, Faculty of Science and Engineering, Macquarie University(麦考瑞大学计算机系);Machine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学机器学习系)