2 papers
cs.LG2023★ 9 cited
Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets
James Chapman, Bohan Chen, Zheng Tan +3
Active learning improves the performance of machine learning methods by judiciously selecting a limited number of unlabeled data points to query for labels, with the aim of maximal…
cs.NI2021
Efficient and Reliable Overlay Networks for Decentralized Federated Learning
Yifan Hua, Kevin Miller, Andrea L. Bertozzi +2
We propose near-optimal overlay networks based on -regular expander graphs to accelerate decentralized federated learning (DFL) and improve its generalization. In DFL a massive…