4 papers
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…
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…
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…
Reliable IoT Storage: Minimizing Bandwidth Use in Storage Without Newcomer Nodes
Xiaobo Zhao, Daniel E. Lucani, Xiaohong Shen +1
This letter characterizes the optimal policies for bandwidth use and storage for the problem of distributed storage in Internet of Things (IoT) scenarios, where lost nodes cannot b…