Personalized Federated Learning with First Order Model Optimization

Michael Zhang, Karan Sapra, Sanja Fidler, Serena Yeung, Jose M. Alvarez

Keywords: Federated learning, personalized learning

Abstract: 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. Here we propose an alternative, where each client only federates with other relevant clients to obtain a stronger model per client-specific objectives. To achieve this personalization, rather than computing a single model average with constant weights for the entire federation as in traditional FL, we efficiently calculate optimal weighted model combinations for each client, based on figuring out how much a client can benefit from another's model. We do not assume knowledge of any underlying data distributions or client similarities, and allow each client to optimize for arbitrary target distributions of interest, enabling greater flexibility for personalization. We evaluate and characterize our method on a variety of federated settings, datasets, and degrees of local data heterogeneity. Our method outperforms existing alternatives, while also enabling new features for personalized FL such as transfer outside of local data distributions.

One-sentence Summary: We propose a new federated learning framework that efficiently computes a personalized weighted combination of available models for each client, outperforming existing work for personalized federated learning.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CIFAR-100](https://paperswithcode.com/dataset/cifar-100), [MNIST](https://paperswithcode.com/dataset/mnist)

Code: [ NVlabs/FedFomo](https://github.com/NVlabs/FedFomo) + [ 2 community implementations](https://paperswithcode.com/paper/?openreview=ehJqJQk9cw)

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/arxiv:2012.08565/code)