Federated Multi-armed Bandits with Personalization
- URL: http://arxiv.org/abs/2102.13101v1
- Date: Thu, 25 Feb 2021 18:59:43 GMT
- Title: Federated Multi-armed Bandits with Personalization
- Authors: Chengshuai Shi, Cong Shen, Jing Yang
- Abstract summary: We propose a new bandit paradigm analogous to the federated learning (FL) framework in supervised learning.
Under the PF-MAB framework, a mixed bandit learning problem that flexibly balances generalization and personalization is studied.
We then propose the Personalized Federated Upper Confidence Bound (PF-UCB) algorithm, where the exploration length is chosen carefully.
- Score: 19.85013388155711
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A general framework of personalized federated multi-armed bandits (PF-MAB) is
proposed, which is a new bandit paradigm analogous to the federated learning
(FL) framework in supervised learning and enjoys the features of FL with
personalization. Under the PF-MAB framework, a mixed bandit learning problem
that flexibly balances generalization and personalization is studied. A lower
bound analysis for the mixed model is presented. We then propose the
Personalized Federated Upper Confidence Bound (PF-UCB) algorithm, where the
exploration length is chosen carefully to achieve the desired balance of
learning the local model and supplying global information for the mixed
learning objective. Theoretical analysis proves that PF-UCB achieves an
$O(\log(T))$ regret regardless of the degree of personalization, and has a
similar instance dependency as the lower bound. Experiments using both
synthetic and real-world datasets corroborate the theoretical analysis and
demonstrate the effectiveness of the proposed algorithm.
Related papers
- On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness [16.595935469099306]
We propose FLAME, an optimization framework by utilizing the alternating direction method of multipliers (ADMM) to train personalized and global models.
Our theoretical analysis establishes the global convergence and two kinds of convergence rates for FLAME under mild assumptions.
Our experimental findings show that FLAME outperforms state-of-the-art methods in convergence and accuracy, and it achieves higher test accuracy under various attacks.
arXiv Detail & Related papers (2024-07-23T11:35:42Z) - Federated Learning with Projected Trajectory Regularization [65.6266768678291]
Federated learning enables joint training of machine learning models from distributed clients without sharing their local data.
One key challenge in federated learning is to handle non-identically distributed data across the clients.
We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
arXiv Detail & Related papers (2023-12-22T02:12:08Z) - Aggregation Weighting of Federated Learning via Generalization Bound
Estimation [65.8630966842025]
Federated Learning (FL) typically aggregates client model parameters using a weighting approach determined by sample proportions.
We replace the aforementioned weighting method with a new strategy that considers the generalization bounds of each local model.
arXiv Detail & Related papers (2023-11-10T08:50:28Z) - Every Parameter Matters: Ensuring the Convergence of Federated Learning
with Dynamic Heterogeneous Models Reduction [22.567754688492414]
Cross-device Federated Learning (FL) faces significant challenges where low-end clients that could potentially make unique contributions are excluded from training large models due to their resource bottlenecks.
Recent research efforts have focused on model-heterogeneous FL, by extracting reduced-size models from the global model and applying them to local clients accordingly.
This paper presents a unifying framework for heterogeneous FL algorithms with online model extraction and provides a general convergence analysis for the first time.
arXiv Detail & Related papers (2023-10-12T19:07:58Z) - Tackling Computational Heterogeneity in FL: A Few Theoretical Insights [68.8204255655161]
We introduce and analyse a novel aggregation framework that allows for formalizing and tackling computational heterogeneous data.
Proposed aggregation algorithms are extensively analyzed from a theoretical, and an experimental prospective.
arXiv Detail & Related papers (2023-07-12T16:28:21Z) - FedCBO: Reaching Group Consensus in Clustered Federated Learning through
Consensus-based Optimization [1.911678487931003]
Federated learning seeks to integrate the training learning models from multiple users, each user having their own data set, in a way that is sensitive to data privacy and to communication loss constraints.
In this paper, we propose a novel solution to a global, clustered problem of federated learning that is inspired by ideas in consensus-based optimization (CBO)
Our new CBO-type method is based on a system of interacting particles that is oblivious to group.
arXiv Detail & Related papers (2023-05-04T15:02:09Z) - Fusion of Global and Local Knowledge for Personalized Federated Learning [75.20751492913892]
In this paper, we explore personalized models with low-rank and sparse decomposition.
We propose a two-stage-based algorithm named textbfFederated learning with mixed textbfSparse and textbfRank representation.
Under proper assumptions, we show that the GKR trained by FedSLR can at least sub-linearly converge to a stationary point of the regularized problem.
arXiv Detail & Related papers (2023-02-21T23:09:45Z) - Proof of Swarm Based Ensemble Learning for Federated Learning
Applications [3.2536767864585663]
In federated learning it is not feasible to apply centralised ensemble learning directly due to privacy concerns.
Most distributed consensus algorithms, such as Byzantine fault tolerance (BFT), do not normally perform well in such applications.
We propose PoSw, a novel distributed consensus algorithm for ensemble learning in a federated setting.
arXiv Detail & Related papers (2022-12-28T13:53:34Z) - Federated Learning Aggregation: New Robust Algorithms with Guarantees [63.96013144017572]
Federated learning has been recently proposed for distributed model training at the edge.
This paper presents a complete general mathematical convergence analysis to evaluate aggregation strategies in a federated learning framework.
We derive novel aggregation algorithms which are able to modify their model architecture by differentiating client contributions according to the value of their losses.
arXiv Detail & Related papers (2022-05-22T16:37:53Z) - 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) - Federated Multi-Armed Bandits [18.95281057580889]
Federated multi-armed bandits (FMAB) is a new bandit paradigm that parallels the federated learning (FL) framework in supervised learning.
This paper proposes a general framework of FMAB and then studies two specific federated bandit models.
We show that, somewhat surprisingly, the order-optimal regret can be achieved independent of the number of clients with a careful choice of the update periodicity.
arXiv Detail & Related papers (2021-01-28T18:59:19Z)
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.