Decentralized Personalized Federated Learning for Min-Max Problems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911842310291456 |
|---|---|
| author | Borodich, Ekaterina Beznosikov, Aleksandr Sadiev, Abdurakhmon Sushko, Vadim Savelyev, Nikolay Takáč, Martin Gasnikov, Alexander |
| author_facet | Borodich, Ekaterina Beznosikov, Aleksandr Sadiev, Abdurakhmon Sushko, Vadim Savelyev, Nikolay Takáč, Martin Gasnikov, Alexander |
| contents | Personalized Federated Learning (PFL) has witnessed remarkable advancements, enabling the development of innovative machine learning applications that preserve the privacy of training data. However, existing theoretical research in this field has primarily focused on distributed optimization for minimization problems. This paper is the first to study PFL for saddle point problems encompassing a broader range of optimization problems, that require more than just solving minimization problems. In this work, we consider a recently proposed PFL setting with the mixing objective function, an approach combining the learning of a global model together with locally distributed learners. Unlike most previous work, which considered only the centralized setting, we work in a more general and decentralized setup that allows us to design and analyze more practical and federated ways to connect devices to the network. We proposed new algorithms to address this problem and provide a theoretical analysis of the smooth (strongly) convex-(strongly) concave saddle point problems in stochastic and deterministic cases. Numerical experiments for bilinear problems and neural networks with adversarial noise demonstrate the effectiveness of the proposed methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_07289 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Decentralized Personalized Federated Learning for Min-Max Problems Borodich, Ekaterina Beznosikov, Aleksandr Sadiev, Abdurakhmon Sushko, Vadim Savelyev, Nikolay Takáč, Martin Gasnikov, Alexander Machine Learning Distributed, Parallel, and Cluster Computing Optimization and Control Personalized Federated Learning (PFL) has witnessed remarkable advancements, enabling the development of innovative machine learning applications that preserve the privacy of training data. However, existing theoretical research in this field has primarily focused on distributed optimization for minimization problems. This paper is the first to study PFL for saddle point problems encompassing a broader range of optimization problems, that require more than just solving minimization problems. In this work, we consider a recently proposed PFL setting with the mixing objective function, an approach combining the learning of a global model together with locally distributed learners. Unlike most previous work, which considered only the centralized setting, we work in a more general and decentralized setup that allows us to design and analyze more practical and federated ways to connect devices to the network. We proposed new algorithms to address this problem and provide a theoretical analysis of the smooth (strongly) convex-(strongly) concave saddle point problems in stochastic and deterministic cases. Numerical experiments for bilinear problems and neural networks with adversarial noise demonstrate the effectiveness of the proposed methods. |
| title | Decentralized Personalized Federated Learning for Min-Max Problems |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing Optimization and Control |
| url | https://arxiv.org/abs/2106.07289 |