paper-with-me

홈 › Papers

Multi-Model Federated Learning

2022-01-07 · Neelkamal Bhuyan, Sharayu Moharir

Federated learning is a form of distributed learning with the key challenge being the non-identically distributed nature of the data in the participating clients. In this paper, we extend federated learning to the setting where multiple unrelated models are trained simultaneously. Specifically, every client is able to train any one of M models at a time and the server maintains a model for each of the M models which is typically a suitably averaged version of the model computed by the clients. We propose multiple policies for assigning learning tasks to clients over time. In the first policy, we extend the widely studied FedAvg to multi-model learning by allotting models to clients in an i.i.d. stochastic manner. In addition, we propose two new policies for client selection in a multi-model federated setting which make decisions based on current local losses for each client-model pair. We compare the performance of the policies on tasks involving synthetic and real-world data and characterize the performance of the proposed policies. The key take-away from our work is that the proposed multi-model policies perform better or at least as good as single model training using FedAvg.

📄 PDF Abstract BibTeX arXiv:2201.02582

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningmodel

Similar Papers 제목 키워드 기반

Variational Federated Multi-Task Learning

2019-06-14 · Luca Corinzia, Ami Beuret, Joachim M. Buhmann

In federated learning, a central server coordinates the training of a single model on a massively distributed network of devices. This setting can be naturally extended to a multi-task learning framework, to handle real-…

Federated LearningMulti-Task LearningVariational Inference

FLAG: Fast Label-Adaptive Aggregation for Multi-label Classification in Federated Learning

2023-02-27 · Shih-Fang Chang, Benny Wei-Yun Hsu, Tien-Yu Chang, Vincent S. Tseng

Federated learning aims to share private data to maximize the data utility without privacy leakage. Previous federated learning research mainly focuses on multi-class classification problems. However, multi-label classif…

ClassificationFederated LearningMulti-class ClassificationMulti-Label Classification+1

Federated Multi-view Matrix Factorization for Personalized Recommendations

2020-04-08 · Adrian Flanagan, Were Oyomno, Alexander Grigorievskiy, Kuan Eeik Tan 외

We introduce the federated multi-view matrix factorization method that extends the federated learning framework to matrix factorization with multiple data sources. Our method is able to learn the multi-view model without…

Federated Learning

Federated Multi-Mini-Batch: An Efficient Training Approach to Federated Learning in Non-IID Environments

2020-11-13 · Reza Nasirigerdeh, Mohammad Bakhtiari, Reihaneh Torkzadehmahani, Amirhossein Bayat 외

Federated learning has faced performance and network communication challenges, especially in the environments where the data is not independent and identically distributed (IID) across the clients. To address the former …

Federated Learning

Federated Multi-Objective Learning

2023-10-15 · NeurIPS 2023 11 · Haibo Yang, Zhuqing Liu, Jia Liu, Chaosheng Dong 외

In recent years, multi-objective optimization (MOO) emerges as a foundational problem underpinning many multi-agent multi-task learning applications. However, existing algorithms in MOO literature remain limited to centr…

Federated LearningMulti-Task Learning