GPFL: A Gradient Projection-Based Client Selection Framework for Efficient Federated Learning

• URL: http://arxiv.org/abs/2403.17833v2
• Date: Sun, 26 May 2024 06:34:29 GMT
• Title: GPFL: A Gradient Projection-Based Client Selection Framework for Efficient Federated Learning
• Authors: Shijie Na, Yuzhi Liang, Siu-Ming Yiu,
• Abstract summary: Federated learning client selection is crucial for determining participant clients. We propose GPFL, which measures client value by comparing local and global descent directions. GPFL exhibits shorter computation times through pre-selection and parameter reuse in federated learning.
• Score: 6.717563725609496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated learning client selection is crucial for determining participant clients while balancing model accuracy and communication efficiency. Existing methods have limitations in handling data heterogeneity, computational burdens, and independent client treatment. To address these challenges, we propose GPFL, which measures client value by comparing local and global descent directions. We also employ an Exploit-Explore mechanism to enhance performance. Experimental results on FEMINST and CIFAR-10 datasets demonstrate that GPFL outperforms baselines in Non-IID scenarios, achieving over 9\% improvement in FEMINST test accuracy. Moreover, GPFL exhibits shorter computation times through pre-selection and parameter reuse in federated learning.

Related papers

• Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning [14.866327821524854]
  HiCS-FL is a novel client selection method in which the server estimates statistical heterogeneity of a client's data using the client's update of the network's output layer. In non-IID settings HiCS-FL achieves faster convergence than state-of-the-art FL client selection schemes.
  arXiv  Detail & Related papers  (2023-09-30T00:29:30Z)
• FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data [54.81695390763957]
  Federated learning is an emerging distributed machine learning method. We propose a heterogeneous local variant of AMSGrad, named FedLALR, in which each client adjusts its learning rate. We show that our client-specified auto-tuned learning rate scheduling can converge and achieve linear speedup with respect to the number of clients.
  arXiv  Detail & Related papers  (2023-09-18T12:35:05Z)
• 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)
• DPP-based Client Selection for Federated Learning with Non-IID Data [97.1195165400568]
  This paper proposes a client selection (CS) method to tackle the communication bottleneck of federated learning (FL) We first analyze the effect of CS in FL and show that FL training can be accelerated by adequately choosing participants to diversify the training dataset in each round of training. We leverage data profiling and determinantal point process (DPP) sampling techniques to develop an algorithm termed Federated Learning with DPP-based Participant Selection (FL-DP$3$S)
  arXiv  Detail & Related papers  (2023-03-30T13:14:54Z)
• FilFL: Client Filtering for Optimized Client Participation in Federated Learning [71.46173076298957]
  Federated learning enables clients to collaboratively train a model without exchanging local data. Clients participating in the training process significantly impact the convergence rate, learning efficiency, and model generalization. We propose a novel approach, client filtering, to improve model generalization and optimize client participation and training.
  arXiv  Detail & Related papers  (2023-02-13T18:55:31Z)
• Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction [76.26710990597498]
  We show that the class-imbalance of the grouped data from randomly selected clients can lead to significant performance degradation. Based on our key observation, we design an efficient client sampling mechanism, i.e., Federated Class-balanced Sampling (Fed-CBS) In particular, we propose a measure of class-imbalance and then employ homomorphic encryption to derive this measure in a privacy-preserving way.
  arXiv  Detail & Related papers  (2022-09-30T05:42:56Z)
• Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints [29.897785907692644]
  Federated learning systems operate in settings with intermittent client availability and/or time-varying communication constraints. We propose F3AST, an unbiased algorithm that learns an availability-dependent client selection strategy. We show up to 186% and 8% accuracy improvements over FedAvg, and 8% and 7% over FedAdam on CIFAR100 and Shakespeare, respectively.
  arXiv  Detail & Related papers  (2022-05-13T16:08:58Z)
• Personalized Federated Learning with Gaussian Processes [24.102107455189454]
  Federated learning aims to learn a global model that performs well on client devices with limited cross-client communication. We present pFedGP, a solution to PFL that is based on Gaussian processes (GPs) with deep kernel learning. pFedGP achieves well-calibrated predictions while significantly outperforming baseline methods, reaching up to 21% in accuracy gain.
  arXiv  Detail & Related papers  (2021-06-29T15:09:13Z)
• Towards Fair Federated Learning with Zero-Shot Data Augmentation [123.37082242750866]
  Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models while having no access to the client data. We propose a novel federated learning system that employs zero-shot data augmentation on under-represented data to mitigate statistical heterogeneity and encourage more uniform accuracy performance across clients in federated networks. We study two variants of this scheme, Fed-ZDAC (federated learning with zero-shot data augmentation at the clients) and Fed-ZDAS (federated learning with zero-shot data augmentation at the server).
  arXiv  Detail & Related papers  (2021-04-27T18:23:54Z)
• Budgeted Online Selection of Candidate IoT Clients to Participate in Federated Learning [33.742677763076]
  Federated Learning (FL) is an architecture in which model parameters are exchanged instead of client data. FL trains a global model by communicating with clients over communication rounds. We propose an online stateful FL to find the best candidate clients and an IoT client alarm application.
  arXiv  Detail & Related papers  (2020-11-16T06:32:31Z)
• Oort: Efficient Federated Learning via Guided Participant Selection [5.01181273401802]
  Federated Learning (FL) enables in-situ model training and testing on edge data. Existing efforts randomly select FL participants, which leads to poor model and system efficiency. Oort improves time-to-accuracy performance by 1.2x-14.1x and final model accuracy by 1.3%-9.8%.
  arXiv  Detail & Related papers  (2020-10-12T23:48:30Z)

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.