Personalized Federated Learning
19 papers with code • 3 benchmarks • 2 datasets
The federated learning setup presents numerous challenges including data heterogeneity (differences in data distribution), device heterogeneity (in terms of computation capabilities, network connection, etc.), and communication efficiency. Especially data heterogeneity makes it hard to learn a single shared global model that applies to all clients. To overcome these issues, Personalized Federated Learning (PFL) aims to personalize the global model for each client in the federation.
LibrariesUse these libraries to find Personalized Federated Learning models and implementations
Federated learning (FL) is a decentralized and privacy-preserving machine learning technique in which a group of clients collaborate with a server to learn a global model without sharing clients' data.
Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach
In this paper, we study a personalized variant of the federated learning in which our goal is to find an initial shared model that current or new users can easily adapt to their local dataset by performing one or a few steps of gradient descent with respect to their own data.
Based on this intuition, we propose a novel federated learning framework and algorithm for learning a shared data representation across clients and unique local heads for each client.
Non-Independent and Identically Distributed (non- IID) data distribution among clients is considered as the key factor that degrades the performance of federated learning (FL).
In this research, a segmented federated learning is proposed, different from a collaborative learning based on single global model in a traditional federated learning model, it keeps multiple global models which allow each segment of participants to conduct collaborative learning separately and rearranges the segmentation of participants dynamically as well.
While federated learning traditionally aims to train a single global model across decentralized local datasets, one model may not always be ideal for all participating clients.
Adaptive Intrusion Detection in the Networking of Large-Scale LANs with Segmented Federated Learning
We propose Segmented-Federated Learning (Segmented-FL), where by employing periodic local model evaluation and network segmentation, we aim to bring similar network environments to the same group.
To achieve model personalization while maintaining generalization, in this paper, we propose a new approach, named PFL-MoE, which mixes outputs of the personalized model and global model via the MoE architecture.