paper-with-me

Papers

Improving Federated Learning Personalization via Model Agnostic Meta Learning

2019-09-27 · Yihan Jiang, Jakub Konečný, Keith Rush, Sreeram Kannan

Federated Learning (FL) refers to learning a high quality global model based on decentralized data storage, without ever copying the raw data. A natural scenario arises with data created on mobile phones by the activity of their users. Given the typical data heterogeneity in such situations, it is natural to ask how can the global model be personalized for every such device, individually. In this work, we point out that the setting of Model Agnostic Meta Learning (MAML), where one optimizes for a fast, gradient-based, few-shot adaptation to a heterogeneous distribution of tasks, has a number of similarities with the objective of personalization for FL. We present FL as a natural source of practical applications for MAML algorithms, and make the following observations. 1) The popular FL algorithm, Federated Averaging, can be interpreted as a meta learning algorithm. 2) Careful fine-tuning can yield a global model with higher accuracy, which is at the same time easier to personalize. However, solely optimizing for the global model accuracy yields a weaker personalization result. 3) A model trained using a standard datacenter optimization method is much harder to personalize, compared to one trained using Federated Averaging, supporting the first claim. These results raise new questions for FL, MAML, and broader ML research.

📄 PDF Abstract BibTeX arXiv:1909.12488

Code (4)

KarhouTam/Personalized-FedAvg
MindSpore-scientific/code-12/tree/main/FSMAFL mindspore
pwc-1/Paper-9/tree/main/6/FSMAFL mindspore
xiuyu0000/new_papers_codes/tree/main/FSMAFL mindspore

Tasks

Federated LearningMeta-Learning

Methods 이 논문이 사용한 방법론

MAML 설명 없음

Similar Papers 제목 키워드 기반

FedL2P: Federated Learning to Personalize

2023-09-21 · NeurIPS 2023 11

Federated learning (FL) research has made progress in developing algorithms for distributed learning of global models, as well as algorithms for local personalization of those common models to the specifics of each clien…

PersA-FL: Personalized Asynchronous Federated Learning

2022-10-03 · Mohammad Taha Toghani, Soomin Lee, César A. Uribe

We study the personalized federated learning problem under asynchronous updates. In this problem, each client seeks to obtain a personalized model that simultaneously outperforms local and global models. We consider two …

Federated LearningMeta-LearningPersonalized Federated Learning

Federated Reconstruction: Partially Local Federated Learning

2021-02-05 · NeurIPS 2021 12 · Karan Singhal, Hakim Sidahmed, Zachary Garrett, Shanshan Wu 외

Personalization methods in federated learning aim to balance the benefits of federated and local training for data availability, communication cost, and robustness to client heterogeneity. Approaches that require clients…

Collaborative FilteringFederated LearningMeta-Learning

Motley: Benchmarking Heterogeneity and Personalization in Federated Learning

2022-06-18 · Shanshan Wu, Tian Li, Zachary Charles, Yu Xiao 외

Personalized federated learning considers learning models unique to each client in a heterogeneous network. The resulting client-specific models have been purported to improve metrics such as accuracy, fairness, and robu…

BenchmarkingFairnessFederated LearningMeta-Learning+3

Elastically-Constrained Meta-Learner for Federated Learning

2023-06-29 · Peng Lan, Donglai Chen, Chong Xie, Keshu Chen 외

Federated learning is an approach to collaboratively training machine learning models for multiple parties that prohibit data sharing. One of the challenges in federated learning is non-IID data between clients, as a sin…

Federated LearningMeta-Learning