T Qi, Y Zhan, P Li, J Guo, Y Xia - arXiv preprint arXiv:2308.10298, 2023 - arxiv.org
Federated learning (FL) enables collaborative model training among distributed devices without data sharing, but existing FL suffers from poor scalability because of global model …
Federated Learning (FL) has emerged as a powerful approach that enables collaborative distributed model training without the need for data sharing. However, FL grapples with …
Federated Learning (FL) enables multiple devices to collaboratively train a shared model while ensuring data privacy. The selection of participating devices in each training round …
Federated Learning faces significant challenges in statistical and system heterogeneity, along with high energy consumption, necessitating efficient client selection strategies …
Y Wu, L Li, C Tian, C Xu - arXiv preprint arXiv:2404.13349, 2024 - arxiv.org
This paper presents ProFL, a novel progressive FL framework to effectively break the memory wall. Specifically, ProFL divides the model into different blocks based on its original …
In this paper, we propose SmartFreeze, a framework that effectively reduces the memory footprint by conducting the training in a progressive manner. Instead of updating the full …
Federated Learning coordinates multiple clients to collaboratively train a shared model while preserving data privacy. However, the training data with noisy labels located on the …
Real-world deployment of federated learning requires orchestrating clients with widely varied compute resources, from strong enterprise-grade devices in data centers to weak …
C Wang, Z Zhou, X Zhang… - 2024 IEEE 44th …, 2024 - ieeexplore.ieee.org
Federated learning (FL), a decentralized machine learning approach, enables privacy- preserving and collaborative model training without centralizing sensitive data. It has been …