Personalized Federated Learning through Local Memorization

Othmane Marfoq, Giovanni Neglia, Richard Vidal, Laetitia Kameni
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:15070-15092, 2022.

Abstract

Federated learning allows clients to collaboratively learn statistical models while keeping their data local. Federated learning was originally used to train a unique global model to be served to all clients, but this approach might be sub-optimal when clients’ local data distributions are heterogeneous. In order to tackle this limitation, recent personalized federated learning methods train a separate model for each client while still leveraging the knowledge available at other clients. In this work, we exploit the ability of deep neural networks to extract high quality vectorial representations (embeddings) from non-tabular data, e.g., images and text, to propose a personalization mechanism based on local memorization. Personalization is obtained by interpolating a collectively trained global model with a local $k$-nearest neighbors (kNN) model based on the shared representation provided by the global model. We provide generalization bounds for the proposed approach in the case of binary classification, and we show on a suite of federated datasets that this approach achieves significantly higher accuracy and fairness than state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-marfoq22a, title = {Personalized Federated Learning through Local Memorization}, author = {Marfoq, Othmane and Neglia, Giovanni and Vidal, Richard and Kameni, Laetitia}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {15070--15092}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/marfoq22a/marfoq22a.pdf}, url = {https://proceedings.mlr.press/v162/marfoq22a.html}, abstract = {Federated learning allows clients to collaboratively learn statistical models while keeping their data local. Federated learning was originally used to train a unique global model to be served to all clients, but this approach might be sub-optimal when clients’ local data distributions are heterogeneous. In order to tackle this limitation, recent personalized federated learning methods train a separate model for each client while still leveraging the knowledge available at other clients. In this work, we exploit the ability of deep neural networks to extract high quality vectorial representations (embeddings) from non-tabular data, e.g., images and text, to propose a personalization mechanism based on local memorization. Personalization is obtained by interpolating a collectively trained global model with a local $k$-nearest neighbors (kNN) model based on the shared representation provided by the global model. We provide generalization bounds for the proposed approach in the case of binary classification, and we show on a suite of federated datasets that this approach achieves significantly higher accuracy and fairness than state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Personalized Federated Learning through Local Memorization %A Othmane Marfoq %A Giovanni Neglia %A Richard Vidal %A Laetitia Kameni %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-marfoq22a %I PMLR %P 15070--15092 %U https://proceedings.mlr.press/v162/marfoq22a.html %V 162 %X Federated learning allows clients to collaboratively learn statistical models while keeping their data local. Federated learning was originally used to train a unique global model to be served to all clients, but this approach might be sub-optimal when clients’ local data distributions are heterogeneous. In order to tackle this limitation, recent personalized federated learning methods train a separate model for each client while still leveraging the knowledge available at other clients. In this work, we exploit the ability of deep neural networks to extract high quality vectorial representations (embeddings) from non-tabular data, e.g., images and text, to propose a personalization mechanism based on local memorization. Personalization is obtained by interpolating a collectively trained global model with a local $k$-nearest neighbors (kNN) model based on the shared representation provided by the global model. We provide generalization bounds for the proposed approach in the case of binary classification, and we show on a suite of federated datasets that this approach achieves significantly higher accuracy and fairness than state-of-the-art methods.
APA
Marfoq, O., Neglia, G., Vidal, R. & Kameni, L.. (2022). Personalized Federated Learning through Local Memorization. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:15070-15092 Available from https://proceedings.mlr.press/v162/marfoq22a.html.

Related Material