Privacy-Aware Multi-Device Cooperative Edge Inference with Distributed Resource Bidding
This addresses privacy concerns for mobile devices in edge computing AI applications, but it is incremental as it builds on existing cooperative inference methods with a new bidding and compression approach.
The paper tackles privacy leakage in multi-device cooperative edge inference for classification tasks by integrating a distributed bidding mechanism for computational resources and using intermediate feature compression, achieving 0.31-0.95% improvements in classification accuracy under privacy constraints and up to 1.67% gains by considering data difficulty.
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.