多设备协作推理中兼顾隐私与效率，通过竞价分配算力资源。
Privacy-Aware Multi-Device Cooperative Edge Inference with Distributed Resource Bidding
- 采用分布式竞价机制分配边缘计算资源，降低隐私泄露风险。
- 在保障隐私前提下，分类准确率提升0.31%-0.95%。
- 适合对数据隐私敏感的移动智能应用，如医疗、金融场景。
移动边缘计算（MEC）使移动设备可通过与邻近边缘服务器协作，支持人工智能应用。然而，设备-边缘协同推理面临日益突出的数据隐私问题。本文提出一种面向分类任务的隐私感知多设备协同边缘推理系统，引入分布式资源竞价机制。通过中间特征压缩作为减少隐私泄露的规范方法，为在分布式环境下确定竞价值与特征压缩比，构建了去中心化的部分可观测马尔可夫决策过程（DEC-POMDP）模型，并设计基于多智能体深度确定性策略梯度（MADDPG）的算法。仿真结果表明，所提算法在保证足够数据隐私保护的前提下，相比忽略无线信道条件的方法，分类准确率提升0.31%-0.95%；进一步考虑推理数据难度后，性能再提升1.54%-1.67%。
原文摘要 · Abstract (English)
Mobile edge computing (MEC) has empowered mobile devices (MDs) in supporting artificial intelligence (AI) applications through collaborative efforts with proximal MEC servers. Unfortunately, despite the great promise of device-edge cooperative AI inference, data privacy becomes an increasing concern. In this paper, we develop a privacy-aware multi-device cooperative edge inference system for classification tasks, which integrates a distributed bidding mechanism for the MEC server's computational resources. Intermediate feature compression is adopted as a principled approach to minimize data privacy leakage. To determine the bidding values and feature compression ratios in a distributed fashion, we formulate a decentralized partially observable Markov decision process (DEC-POMDP) model, for which, a multi-agent deep deterministic policy gradient (MADDPG)-based algorithm is developed. Simulation results demonstrate the effectiveness of the proposed algorithm in privacy-preserving cooperative edge inference. Specifically, given a sufficient level of data privacy protection, the proposed algorithm achieves 0.31-0.95% improvements in classification accuracy compared to the approach being agnostic to the wireless channel conditions. The performance is further enhanced by 1.54-1.67% by considering the difficulties of inference data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。