PEFLL: Personalized federated learning by learning to learn
Scott JA, Zakerinia H, Lampert C. 2024. PEFLL: Personalized federated learning by learning to learn. 12th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.
Download
Conference Paper
| Published
| English
Scopus indexed
Department
Abstract
We present PeFLL, a new personalized federated learning algorithm that improves
over the state-of-the-art in three aspects: 1) it produces more accurate models,
especially in the low-data regime, and not only for clients present during its
training phase, but also for any that may emerge in the future; 2) it reduces the
amount of on-client computation and client-server communication by providing
future clients with ready-to-use personalized models that require no additional
finetuning or optimization; 3) it comes with theoretical guarantees that establish
generalization from the observed clients to future ones.
At the core of PeFLL lies a learning-to-learn approach that jointly trains an
embedding network and a hypernetwork. The embedding network is used to
represent clients in a latent descriptor space in a way that reflects their similarity
to each other. The hypernetwork takes as input such descriptors and outputs the
parameters of fully personalized client models. In combination, both networks
constitute a learning algorithm that achieves state-of-the-art performance in several
personalized federated learning benchmarks
Publishing Year
Date Published
2024-03-07
Proceedings Title
12th International Conference on Learning Representations
Acknowledgement
This research was supported by the Scientific Service Units (SSU) of ISTA through resources provided by Scientific Computing (SciComp).
Acknowledged SSUs
Conference
ICLR: International Conference on Learning Representations
Conference Location
Vienna, Austria
Conference Date
2024-03-07 – 2024-03-07
IST-REx-ID
Cite this
Scott JA, Zakerinia H, Lampert C. PEFLL: Personalized federated learning by learning to learn. In: 12th International Conference on Learning Representations. OpenReview; 2024.
Scott, J. A., Zakerinia, H., & Lampert, C. (2024). PEFLL: Personalized federated learning by learning to learn. In 12th International Conference on Learning Representations. Vienna, Austria: OpenReview.
Scott, Jonathan A, Hossein Zakerinia, and Christoph Lampert. “PEFLL: Personalized Federated Learning by Learning to Learn.” In 12th International Conference on Learning Representations. OpenReview, 2024.
J. A. Scott, H. Zakerinia, and C. Lampert, “PEFLL: Personalized federated learning by learning to learn,” in 12th International Conference on Learning Representations, Vienna, Austria, 2024.
Scott JA, Zakerinia H, Lampert C. 2024. PEFLL: Personalized federated learning by learning to learn. 12th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.
Scott, Jonathan A., et al. “PEFLL: Personalized Federated Learning by Learning to Learn.” 12th International Conference on Learning Representations, OpenReview, 2024.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Main File(s)
File Name
2024_ICLR_Scott.pdf
1.03 MB
Access Level
Open Access
Date Uploaded
2024-08-12
MD5 Checksum
81b7ea2e667adaf9c7a7b6b376b1f251
Export
Marked PublicationsOpen Data ISTA Research Explorer
Sources
arXiv 2306.05515