Private Collaborative Edge Inference via Over-the-Air Computation

2024-07-30

IEEE Transactions on Machine Learning in Communications and Networking

AI Summary

Privacy preservation and bandwidth efficiency in wireless edge collaborative inference remain challenging. Method: This paper introduces over-the-air computation (OAC) into multi-user edge ensemble inference for the first time, proposing a privacy-enhanced, bandwidth-efficient multi-view classification framework. It supports client-side local training, parallel decision-making, and distributed model aggregation, leveraging OAC’s analog channel superposition property and a differential privacy–based incentive mechanism to ensure parameter-level privacy at clients while enabling global inference. Contribution/Results: Experiments demonstrate statistically significant improvements in inference accuracy over orthogonal transmission schemes (p < 0.01) and over 50% reduction in communication overhead. The implementation is publicly available as open-source code.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Distributed Search
• Computer Vision: Bias, Fairness & Privacy

Application Category

• Security and Privacy: Privacy-enhancing technologies
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

We consider collaborative inference at the wireless edge, where each client's model is trained independently on its local dataset. Clients are queried in parallel to make an accurate decision collaboratively. In addition to maximizing the inference accuracy, we also want to ensure the privacy of local models. To this end, we leverage the superposition property of the multiple access channel to implement bandwidth-efficient multi-user inference methods. We propose different methods for ensemble and multi-view classification that exploit over-the-air computation (OAC). We show that these schemes perform better than their orthogonal counterparts with statistically significant differences while using fewer resources and providing privacy guarantees. We also provide experimental results verifying the benefits of the proposed OAC approach to multi-user inference, and perform an ablation study to demonstrate the effectiveness of our design choices. We share the source code of the framework publicly on Github to facilitate further research and reproducibility.

Problem

• Privacy Preservation
• Multi-device Collaboration
• Bandwidth Efficiency

Innovation

• Privacy Preservation
• Collaborative Edge Computing
• Airborne Computation