Academic Journal
Private Collaborative Edge Inference via Over-the-Air Computation
| Title: | Private Collaborative Edge Inference via Over-the-Air Computation |
|---|---|
| Authors: | Selim F. Yilmaz, Burak Hasircioglu, Li Qiao, Deniz Gunduz |
| Source: | IEEE Transactions on Machine Learning in Communications and Networking, Vol 3, Pp 215-231 (2025) |
| Publisher Information: | IEEE, 2025. |
| Publication Year: | 2025 |
| Collection: | LCC:Electronic computers. Computer science LCC:Telecommunication |
| Subject Terms: | Edge inference, collaborative inference, distributed inference, ensemble, multi-view, over-the-air computation (OAC), Electronic computers. Computer science, QA75.5-76.95, Telecommunication, TK5101-6720 |
| More Details: | 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. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English |
| ISSN: | 2831-316X |
| Relation: | https://ieeexplore.ieee.org/document/10829586/; https://doaj.org/toc/2831-316X |
| DOI: | 10.1109/TMLCN.2025.3526551 |
| Access URL: | https://doaj.org/article/9f5bdf818ef04549afbf7ad14814dc26 |
| Accession Number: | edsdoj.9f5bdf818ef04549afbf7ad14814dc26 |
| Database: | Directory of Open Access Journals |
| ISSN: | 2831316X |
|---|---|
| DOI: | 10.1109/TMLCN.2025.3526551 |
| Published in: | IEEE Transactions on Machine Learning in Communications and Networking |
| Language: | English |