Federated Hyperdimensional Computing

no code implementations • 26 Dec 2023 • Kazim Ergun, Rishikanth Chandrasekaran, Tajana Rosing

The strategies we propose to improve the communication efficiency enable our design to reduce communication costs by 66$\times$ vs. DNNs, local client compute and energy consumption by ~1. 5 - 6$\times$, while being highly robust to network errors.

Contrastive Learning Federated Learning