Federated Variational Inference: Towards Improved Personalization and Generalization

• URL: http://arxiv.org/abs/2305.13672v2
• Date: Thu, 25 May 2023 21:07:53 GMT
• Title: Federated Variational Inference: Towards Improved Personalization and Generalization
• Authors: Elahe Vedadi, Joshua V. Dillon, Philip Andrew Mansfield, Karan Singhal, Arash Afkanpour, Warren Richard Morningstar
• Abstract summary: We study personalization and generalization in stateless cross-device federated learning setups. We first propose a hierarchical generative model and formalize it using Bayesian Inference. We then approximate this process using Variational Inference to train our model efficiently. We evaluate our model on FEMNIST and CIFAR-100 image classification and show that FedVI beats the state-of-the-art on both tasks.
• Score: 2.37589914835055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conventional federated learning algorithms train a single global model by leveraging all participating clients' data. However, due to heterogeneity in client generative distributions and predictive models, these approaches may not appropriately approximate the predictive process, converge to an optimal state, or generalize to new clients. We study personalization and generalization in stateless cross-device federated learning setups assuming heterogeneity in client data distributions and predictive models. We first propose a hierarchical generative model and formalize it using Bayesian Inference. We then approximate this process using Variational Inference to train our model efficiently. We call this algorithm Federated Variational Inference (FedVI). We use PAC-Bayes analysis to provide generalization bounds for FedVI. We evaluate our model on FEMNIST and CIFAR-100 image classification and show that FedVI beats the state-of-the-art on both tasks.

Related papers

• FedImpro: Measuring and Improving Client Update in Federated Learning [77.68805026788836]
  Federated Learning (FL) models often experience client drift caused by heterogeneous data. We present an alternative perspective on client drift and aim to mitigate it by generating improved local models.
  arXiv  Detail & Related papers  (2024-02-10T18:14:57Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts [24.196279060605402]
  We consider a federated learning (FL) system consisting of multiple clients and a server. Unlike the conventional FL framework that assumes the client's data is static, we consider scenarios where the clients' data distributions may be reshaped by the deployed decision model.
  arXiv  Detail & Related papers  (2023-05-08T23:29:24Z)
• FedHB: Hierarchical Bayesian Federated Learning [11.936836827864095]
  We propose a novel hierarchical Bayesian approach to Federated Learning (FL) Our model reasonably describes the generative process of clients' local data via hierarchical Bayesian modeling. We show that our block-coordinate FL algorithm converges to an optimum of the objective at the rate of $O(sqrtt)$.
  arXiv  Detail & Related papers  (2023-05-08T18:21:41Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• FedAvg with Fine Tuning: Local Updates Lead to Representation Learning [54.65133770989836]
  Federated Averaging (FedAvg) algorithm consists of alternating between a few local gradient updates at client nodes, followed by a model averaging update at the server. We show that the reason behind generalizability of the FedAvg's output is its power in learning the common data representation among the clients' tasks. We also provide empirical evidence demonstrating FedAvg's representation learning ability in federated image classification with heterogeneous data.
  arXiv  Detail & Related papers  (2022-05-27T00:55:24Z)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)
• CD$^2$-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning [24.08509828106899]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to collaboratively learn a shared global model. We propose CD2-pFed, a novel Cyclic Distillation-guided Channel Decoupling framework, to personalize the global model in FL.
  arXiv  Detail & Related papers  (2022-04-08T07:13:30Z)
• Gradient Masked Averaging for Federated Learning [24.687254139644736]
  Federated learning allows a large number of clients with heterogeneous data to coordinate learning of a unified global model. Standard FL algorithms involve averaging of model parameters or gradient updates to approximate the global model at the server. We propose a gradient masked averaging approach for FL as an alternative to the standard averaging of client updates.
  arXiv  Detail & Related papers  (2022-01-28T08:42:43Z)
• Personalized Federated Learning through Local Memorization [10.925242558525683]
  Federated learning allows clients to collaboratively learn statistical models while keeping their data local. Recent personalized federated learning methods train a separate model for each client while still leveraging the knowledge available at other clients. We show on a suite of federated datasets that this approach achieves significantly higher accuracy and fairness than state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-11-17T19:40:07Z)
• Toward Understanding the Influence of Individual Clients in Federated Learning [52.07734799278535]
  Federated learning allows clients to jointly train a global model without sending their private data to a central server. We defined a new notion called em-Influence, quantify this influence over parameters, and proposed an effective efficient model to estimate this metric.
  arXiv  Detail & Related papers  (2020-12-20T14:34:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.