An Aggregation-Free Federated Learning for Tackling Data Heterogeneity

no code implementations • 29 Apr 2024 • YuAn Wang, Huazhu Fu, Renuga Kanagavelu, Qingsong Wei, Yong liu, Rick Siow Mong Goh

FedAF inherently avoids the issue of client drift, enhances the quality of condensed data amid notable data heterogeneity, and improves the global model performance.

Federated Learning

FedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street Views

2 code implementations • 5 Dec 2022 • Renuga Kanagavelu, Kinshuk Dua, Pratik Garai, Susan Elias, Neha Thomas, Simon Elias, Qingsong Wei, Goh Siow Mong Rick, Liu Yong

The need for a Federated approach in this application domain would be to avoid transfer of data from distributed locations and save network bandwidth to reduce communication cost.

Knowledge Distillation Model Compression +1

NV-Tree: Reducing Consistency Cost for NVM-based Single Level Systems

no code implementations • 16 Apr 2015 • Jun Yang, Qingsong Wei, Cheng Chen, Chundong Wang, and Khai Leong Yong, Data Storage Institute, A-STAR; Bingsheng He, Nanyang Technological University

Although the memory fence and CPU cacheline flush instructions can order memory writes to achieve data consistency, they introduce a significant overhead (more than 10X slower in performance).