Private Collaborative Edge Inference via Over-the-Air Computation

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...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Selim F. Yilmaz, Burak Hasircioglu, Li Qiao, Deniz Gunduz
Format:	Artigo
Sprog:	Inglês
Udgivet:	IEEE 2025-01-01
Serier:	IEEE Transactions on Machine Learning in Communications and Networking
Fag:	Edge inference collaborative inference distributed inference ensemble multi-view over-the-air computation (OAC)
Online adgang:	https://ieeexplore.ieee.org/document/10829586/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!