Explicit personalization and local training: Double communication acceleration in federated learning

[PDF] arxiv.org

FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity

K Yi, N Gazagnadou, P Richtárik, L Lyu - arXiv preprint arXiv:2404.09816, 2024 - arxiv.org
The interest in federated learning has surged in recent research due to its unique ability to
train a global model using privacy-secured information held locally on each client. This …
被引用次数：10 相关文章 所有 5 个版本
[PDF] arxiv.org

Adaptive Optimization Algorithms for Machine Learning

S Hanzely - arXiv preprint arXiv:2311.10203, 2023 - arxiv.org
Machine learning assumes a pivotal role in our data-driven world. The increasing scale of
models and datasets necessitates quick and reliable algorithms for model training. This …
被引用次数：3 相关文章 所有 4 个版本
[PDF] arxiv.org

Communication-Efficient Federated Group Distributionally Robust Optimization

Z Guo, T Yang - arXiv preprint arXiv:2410.06369, 2024 - arxiv.org
Federated learning faces challenges due to the heterogeneity in data volumes and
distributions at different clients, which can compromise model generalization ability to …
相关文章 所有 4 个版本
[PDF] openreview.net

Efficient Fully Single-Loop Variance Reduced Methods for Stochastic Bilevel Optimization

K Yi, Y Yu - openreview.net
Stochastic Bilevel Optimization (StocBO) has gained traction given its unique nested
structure, which is increasingly popular in machine learning areas like meta-learning and …
相关文章