Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) has emerged as a promising method to collaboratively learn from decentralized and heterogeneous data available at different clients without the requirement of data ever leaving the clients. Recent works on FL have advocated taking a Bayesian approach to FL as it offers a principled way to account for the model and predictive uncertainty by learning a posterior distribution for the client and/or server models. Moreover, Bayesian FL also naturally enables personalization in FL to handle data heterogeneity across the different clients by having each client learn its own distinct personalized model. In particular, the hierarchical Bayesian approach enables all the clients to learn their personalized models while also taking into account the commonalities via a prior distribution provided by the server. However, despite their promise, Bayesian approaches for FL can be computationally expensive and can have high communication costs as well because of the requirement of computing and sending the posterior distributions. We present a novel Bayesian FL method using an efficient second-order optimization approach, with a computational cost that is similar to first-order optimization methods like Adam, but also provides the various benefits of the Bayesian approach for FL (e.g., uncertainty, personalization), while also being significantly more efficient and accurate than SOTA Bayesian FL methods (both for standard as well as personalized FL settings). Our method achieves improved predictive accuracies as well as better uncertainty estimates as compared to the baselines which include both optimization based as well as Bayesian FL methods.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 27 Nov 2024.
Builds on
28 of 35 references.
References · 28
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
- 2020Personalized Federated Learning with Moreau Envelopescited by 612
- 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
- 2021Towards Personalized Federated Learningcited by 462
- 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
- 2017EMNIST: an extension of MNIST to handwritten letterscited by 212
- 2018Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adamcited by 131
- 2020Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithmscited by 78
- 2023Model Merging by Uncertainty-Based Gradient Matchingcited by 77
16 more
- 2021Personalized Federated Learning with Gaussian Processescited by 76
- 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
- 2017Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Modelscited by 65
- 2024Variational Learning is Effective for Large Deep Networkscited by 62
- 2021FedNL: Making Newton-Type Methods Applicable to Federated Learningcited by 50
- 2021A Bayesian Federated Learning Framework with Online Laplace Approximationcited by 41
- 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
- 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
- 2020Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descentcited by 34
- 2016Patterns of Scalable Bayesian Inferencecited by 24
- 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
- 2023Federated Learning as Variational Inference: A Scalable Expectation Propagation Approachcited by 17
- 2023Confidence-aware Personalized Federated Learning via Variational Expectation Maximizationcited by 17
- 2022Federated Learning with Uncertainty via Distilled Predictive Distributionscited by 11
- 2021On Second-order Optimization Methods for Federated Learningcited by 9
- 2024Federated Bayesian Deep Learning: The Application of Statistical Aggregation Methods to Bayesian Modelscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.