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 2304.01510cs.MAcs.CRcs.DCcs.SYeess.SY
收藏

联邦优化中一种通信高效的本地差分隐私算法

A Communication-efficient Local Differentially Private Algorithm in Federated Optimization

Syed Eqbal Alam, Dhirendra Shukla, Shrisha Rao

AI总结:

针对联邦优化中参数交换导致的隐私泄露问题,提出一种差分隐私的加性增长与乘性递减算法,在保证智能体隐私且通信开销极小的情况下,实现多异构资源的高效分配。

摘要:

联邦优化,即网络中的多个智能体与中央服务器协作以实现网络上的最优社会成本,且无需在智能体之间交换信息,已引起研究界的极大兴趣。在此背景下,智能体根据其本地计算来请求资源。由于与中央服务器交换优化参数(如状态、约束或目标函数),对手可能会推断出智能体的敏感信息。我们开发了一种差分隐私的加性增长与乘性递减算法,用于将多个可分的共享异构资源分配给网络中的智能体。所开发的算法为网络中的每个智能体提供差分隐私保证。该算法不需要智能体间通信,智能体也不需要与其他智能体或中央服务器共享其成本函数或其导数;然而,它们与中央服务器共享其分配状态,以跟踪资源的总消耗。该算法产生的通信开销极小;对于系统中的m个异构资源,在一个时间步通信复杂度的渐近上界为O(m)比特。此外,如果算法在K个时间步内收敛,则通信复杂度上界为O(mK)比特。该算法可应用于多个领域,包括智慧城市、智能能源系统、具有隐私保证的第六代(6G)无线网络资源管理等。我们展示了实验结果以验证算法的有效性。此外,我们提出了隐私与算法效率之间权衡的实证分析。

英文摘要:

Federated optimization, wherein several agents in a network collaborate with a central server to achieve optimal social cost over the network with no requirement for exchanging information among agents, has attracted significant interest from the research community. In this context, agents demand resources based on their local computation. Due to the exchange of optimization parameters such as states, constraints, or objective functions with a central server, an adversary may infer sensitive information of agents. We develop a differentially-private additive-increase and multiplicative-decrease algorithm to allocate multiple divisible shared heterogeneous resources to agents in a network. The developed algorithm provides a differential privacy guarantee to each agent in the network. The algorithm does not require inter-agent communication, and the agents do not need to share their cost function or their derivatives with other agents or a central server; however, they share their allocation states with a central server that keeps track of the aggregate consumption of resources. The algorithm incurs very little communication overhead; for m heterogeneous resources in the system, the asymptotic upper bound on the communication complexity is O(m) bits at a time step. Furthermore, if the algorithm converges in K time steps, then the upper bound communication complexity will be O(mK) bits. The algorithm can find applications in several areas, including smart cities, smart energy systems, resource management in the sixth generation (6G) wireless networks with privacy guarantees, etc. We present experimental results to check the efficacy of the algorithm. Furthermore, we present empirical analyses for the trade-off between privacy and algorithm efficiency.

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。

↑