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 2312.16638cs.LG
收藏

动态设备环境下基于垂直分割数据的鲁棒协作推理

Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environments

Purdue University West Lafeyette(普渡大学西拉法叶分校)

Surojit Ganguli, Zeyu Zhou, Christopher G. Brinton, David I. Inouye

AI总结:

针对动态网络中严重故障下协作推理的鲁棒性问题,提出MAGS方法,通过dropout、复制和gossiping合成模拟故障,在极端故障率下显著提升鲁棒性。

摘要:

当网络中的每个边缘设备仅感知环境的局部信息时,通常需要跨多个设备进行协作推理,以预测环境的全局属性。在安全关键型应用中,协作推理必须对由环境干扰或极端天气引起的严重网络故障保持鲁棒性。现有的协作学习方法,如注重隐私的 Vertical Federated Learning (VFL),通常假设采用集中式设置或某台设备永不发生故障。然而,这些假设使得先前的方法容易受到严重网络故障的影响。为了解决这个问题,我们首先对可能遭遇严重网络故障的动态设备网络上的鲁棒协作推理问题进行了形式化定义。然后,我们开发了一种名为 Multiple Aggregation with Gossip Rounds and Simulated Faults (MAGS) 的简约而有效的方法,该方法通过 dropout、复制和 gossiping 合成模拟故障,从而显著提升了相较于基线方法的鲁棒性。我们还对所提方法进行了理论分析,以解释为何每个组件都能增强鲁棒性。大量实验结果验证了 MAGS 在一系列故障率(包括极端故障率)下均具有鲁棒性。

英文摘要:

When each edge device of a network only perceives a local part of the environment, collaborative inference across multiple devices is often needed to predict global properties of the environment. In safety-critical applications, collaborative inference must be robust to significant network failures caused by environmental disruptions or extreme weather. Existing collaborative learning approaches, such as privacy-focused Vertical Federated Learning (VFL), typically assume a centralized setup or that one device never fails. However, these assumptions make prior approaches susceptible to significant network failures. To address this problem, we first formalize the problem of robust collaborative inference over a dynamic network of devices that could experience significant network faults. Then, we develop a minimalistic yet impactful method called Multiple Aggregation with Gossip Rounds and Simulated Faults (MAGS) that synthesizes simulated faults via dropout, replication, and gossiping to significantly improve robustness over baselines. We also theoretically analyze our proposed approach to explain why each component enhances robustness. Extensive empirical results validate that MAGS is robust across a range of fault rates-including extreme fault rates.

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。

↑