L Yi, H Yu, G Wang, X Liu - arXiv preprint arXiv:2310.13283, 2023 - arxiv.org
Federated learning (FL) is an emerging machine learning paradigm in which a central server coordinates multiple participants (aka FL clients) to train a model collaboratively on …
Federated learning (FL) is a novel distributed machine learning paradigm that enables participants to collaboratively train a centralized model with privacy preservation by …
L Yi, H Yu, C Ren, H Zhang, G Wang, X Liu… - arXiv preprint arXiv …, 2024 - arxiv.org
Federated learning (FL) is widely employed for collaborative training on decentralized data but faces challenges like data, system, and model heterogeneity. This prompted the …
L Yi, H Yu, Z Shi, G Wang, X Liu - arXiv preprint arXiv:2312.09006, 2023 - arxiv.org
Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (aka FL clients) to train the same local model. This …
Recent research in federated large language models (LLMs) has primarily focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on …
L Yi, H Yu, G Wang, X Liu - arXiv preprint arXiv:2311.06879, 2023 - arxiv.org
As a privacy-preserving collaborative machine learning paradigm, federated learning (FL) has attracted significant interest from academia and the industry alike. To allow each data …
L Yi, H Yu, C Ren, H Zhang, G Wang, X Liu… - arXiv preprint arXiv …, 2024 - arxiv.org
Model-heterogeneous personalized federated learning (MHPFL) enables FL clients to train structurally different personalized models on non-independent and identically distributed …
Y Obeidi - arXiv preprint arXiv:2305.19290, 2023 - arxiv.org
Data heterogeneity between clients remains a key challenge in Federated Learning (FL), particularly in the case of tabular data. This work presents Global Layers (GL), a novel partial …
Personalized federated learning (PFL) is designed for scenarios with non-independent and identically distributed (non-IID) client data. Existing model mixup-based methods, one of the …