Over-the-Air Ensemble Inference with Model Privacy

TL;DR

This paper proposes over-the-air ensemble inference methods for distributed wireless edge devices that improve accuracy and privacy while reducing resource use, validated through experiments.

Contribution

It introduces novel over-the-air ensemble inference schemes that outperform traditional methods in accuracy, resource efficiency, and privacy preservation.

Findings

Over-the-air methods outperform orthogonal schemes in accuracy.

Proposed schemes use fewer resources.

Experimental results confirm effectiveness and privacy benefits.

Abstract

We consider distributed inference at the wireless edge, where multiple clients with an ensemble of models, each trained independently on a local dataset, are queried in parallel to make an accurate decision on a new sample. In addition to maximizing inference accuracy, we also want to maximize the privacy of local models. We exploit the superposition property of the air to implement bandwidth-efficient ensemble inference methods. We introduce different over-the-air ensemble methods and show that these schemes perform significantly better than their orthogonal counterparts, while using less resources and providing privacy guarantees. We also provide experimental results verifying the benefits of the proposed over-the-air inference approach, whose source code is shared publicly on Github.