2 papers
cs.LG2024
Federated Split Learning for Human Activity Recognition with Differential Privacy
Josue Ndeko, Shaba Shaon, Aubrey Beal +2
This paper proposes a novel intelligent human activity recognition (HAR) framework based on a new design of Federated Split Learning (FSL) with Differential Privacy (DP) over edge…
cs.LG2023
Unsupervised Representation Learning to Aid Semi-Supervised Meta Learning
Atik Faysal, Mohammad Rostami, Huaxia Wang +2
Few-shot learning or meta-learning leverages the data scarcity problem in machine learning. Traditionally, training data requires a multitude of samples and labeling for supervised…