Conference paper Open Access

Over-the-Air Ensemble Inference with Model Privacy

Yilmaz, Selim F.; Hasırcıoğlu, Burak; Gündüz, Deniz

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.

To appear in IEEE International Symposium on Information Theory (ISIT) 2022
Files (872.7 kB)
Name Size
Over-the-Air Ensemble Inference with Model Privacy.pdf
872.7 kB Download
Views 33
Downloads 25
Data volume 21.8 MB
Unique views 30
Unique downloads 24


Cite as