FedSR: a simple and effective domain generalization method for federated learning
Federated Learning (FL) refers to the decentralized and privacy-preserving machine learning framework in which multiple clients collaborate (with the help of a central server) to train a global model without sharing their data. However, most existing FL methods only focus on maximizing the model...
Main Authors: | Nguyen, AT, Torr, PHS, Lim, S-N |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Curran Associates
2023
|
Similar Items
-
An embarrassingly simple approach to zero-shot learning
by: Romera-Paredes, B, et al.
Published: (2015) -
Gradient matching for domain generalization
by: Shi, Y, et al.
Published: (2022) -
Learn what matters: cross-domain imitation learning with task-relevant embeddings
by: Franzmeyer, T, et al.
Published: (2023) -
GDumb: A simple approach that questions our progress in continual learning
by: Prabhu, A, et al.
Published: (2020) -
KL guided domain adaptation
by: Nguyen, AT, et al.
Published: (2021)