arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.05459cs.ITcs.NIeess.SPmath.IT
收藏

免费隐私:通过自适应功率控制的未编码传输的无线联邦学习

Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control

Dongzhu Liu, Osvaldo Simeone

摘要:

联邦学习(FL)是指分布式协议,该协议避免了参与设备之间的直接原始数据交换,同时为共同的学习任务进行训练。通过这种方式,FL可以潜在地减少通过通信泄露的本地数据集上的信息。然而,为了提供正式的隐私保证,通常需要设置额外的屏蔽机制。当FL通过未编码传输在无线系统中实现时,信道噪声可以直接充当隐私诱导机制。本文证明,只要隐私约束水平,通过差分隐私(DP)测量,是低于一个阈值,随着信噪比(SNR)下降,未编码的传输实现隐私“免费”,即,而不影响学习效果。更一般地说,这项工作研究了自适应功率分配(PA)的分散梯度下降在无线FL的学习最优差距最小化的隐私和功率约束下的目的。正交多址接入(OMA)和非正交多址接入(NOMA)传输与“空中计算”的研究,并获得了离线优化设置的封闭形式的解决方案。此外,启发式在线方法,提出了利用迭代一步提前优化。动态PA的重要性和NOMA与OMA的潜在优势,通过大量的模拟证明。

英文摘要:

Federated Learning (FL) refers to distributed protocols that avoid direct raw data exchange among the participating devices while training for a common learning task. This way, FL can potentially reduce the information on the local data sets that is leaked via communications. In order to provide formal privacy guarantees, however, it is generally necessary to put in place additional masking mechanisms. When FL is implemented in wireless systems via uncoded transmission, the channel noise can directly act as a privacy-inducing mechanism. This paper demonstrates that, as long as the privacy constraint level, measured via differential privacy (DP), is below a threshold that decreases with the signal-to-noise ratio (SNR), uncoded transmission achieves privacy "for free", i.e., without affecting the learning performance. More generally, this work studies adaptive power allocation (PA) for decentralized gradient descent in wireless FL with the aim of minimizing the learning optimality gap under privacy and power constraints. Both orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) transmission with "over-the-air-computing" are studied, and solutions are obtained in closed form for an offline optimization setting. Furthermore, heuristic online methods are proposed that leverage iterative one-step-ahead optimization. The importance of dynamic PA and the potential benefits of NOMA versus OMA are demonstrated through extensive simulations.

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。

↑