5 papers
FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources
Md Sirajul Islam, Isabelle G Chapman, N I Md Ashafuddula +4
Federated Learning (FL) enables collaborative intelligence across decentralized data source devices in a privacy-preserving way. While substantial research attention has been drawn…
Revisiting the Seasonal Trend Decomposition for Enhanced Time Series Forecasting
Sanjeev Panta, Xu Yuan, Li Chen +1
Time series forecasting presents significant challenges in real-world applications across various domains. Building upon the decomposition of the time series, we enhance the archit…
Resource Heterogeneity-Aware and Utilization-Enhanced Scheduling for Deep Learning Clusters
Abeda Sultana, Nabin Pakka, Fei Xu +3
Scheduling deep learning (DL) models to train on powerful clusters with accelerators like GPUs and TPUs, presently falls short, either lacking fine-grained heterogeneity awareness…
SEAFL: Enhancing Efficiency in Semi-Asynchronous Federated Learning through Adaptive Aggregation and Selective Training
Md Sirajul Islam, Sanjeev Panta, Fei Xu +3
Federated Learning (FL) is a promising distributed machine learning framework that allows collaborative learning of a global model across decentralized devices without uploading th…
Incentive-Compatible Federated Learning with Stackelberg Game Modeling
Simin Javaherian, Bryce Turney, Li Chen +1
Federated Learning (FL) has gained prominence as a decentralized machine learning paradigm, allowing clients to collaboratively train a global model while preserving data privacy.…