Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach

A Fallah, A Mokhtari… - Advances in neural …, 2020 - proceedings.neurips.cc
Abstract In Federated Learning, we aim to train models across multiple computing units
(users), while users can only communicate with a common central server, without …
被引用次数：815 相关文章
[PDF] neurips.cc

[PDF][PDF] Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach

A Fallah, A Mokhtari, A Ozdaglar - proceedings.neurips.cc
Abstract In Federated Learning, we aim to train models across multiple computing units
(users), while users can only communicate with a common central server, without …
[PDF] academia.edu

[PDF][PDF] Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach

A Fallah, A Mokhtari, A Ozdaglar - academia.edu
Abstract In Federated Learning, we aim to train models across multiple computing units
(users), while users can only communicate with a common central server, without …

Personalized federated learning with theoretical guarantees: a model-agnostic meta-learning approach

A Fallah, A Mokhtari, A Ozdaglar - Proceedings of the 34th International …, 2020 - dl.acm.org
In Federated Learning, we aim to train models across multiple computing units (users), while
users can only communicate with a common central server, without exchanging their data …
[PDF] archive.org

[PDF][PDF] Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach

A Fallah, A Mokhtari, A Ozdaglar - scholar.archive.org
Abstract In Federated Learning, we aim to train models across multiple computing units
(users), while users can only communicate with a common central server, without …