Search papers, labs, and topics across Lattice.
Department of Computer Engineering, Gebze Technical University, Gebze, Kocaeli, Türkiye
2
5
4
21
Federated learning accuracy jumps by up to 7% simply by using a multi-task autoencoder to identify and filter out noisy or uninformative samples on each client.
Laplacian DP and adaptive quantization can slash federated learning communication costs by over 50% without sacrificing accuracy or privacy, even with non-IID data.