3 papers
cs.LG2026
MUFFLe: Efficient Model Update Compression via Generalized Deduplication for Federated Learning
Xiaobo Zhao, Daniel E. Lucani
Federated learning is well suited to edge environments but is often limited by the uplink cost of transmitting model updates. This Work-in-Progress paper presents MUFFLe, a communi…
cs.DB2026
EntroGD: Scalable Generalized Deduplication for Efficient Direct Analytics on Compressed IoT Data
Xiaobo Zhao, Daniel E. Lucani
Massive data streams from IoT and cyber-physical systems must be processed under strict bandwidth, latency, and resource constraints. Generalized Deduplication (GD) is a promising…
cs.LG2025
dreaMLearning: Data Compression Assisted Machine Learning
Xiaobo Zhao, Aaron Hurst, Panagiotis Karras +1
Despite rapid advancements, machine learning, particularly deep learning, is hindered by the need for large amounts of labeled data to learn meaningful patterns without overfitting…