• Home
  • Search
  • Joint Client-and-Sample Selection for Federated Learning via Bi-Level Optimization
  • Cite Icon2
  • https://doi.org/10.1109/tmc.2024.3455331Copy DOI Icon

Joint Client-and-Sample Selection for Federated Learning via Bi-Level Optimization

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Federated Learning (FL) enables massive local data owners to collaboratively train a deep learning model without disclosing their private data. The importance of local data samples from various data owners to FL models varies widely. This is exacerbated by the presence of noisy data that exhibit large losses similar to important (hard) samples. Currently, there lacks an FL approach that can effectively distinguish hard samples (which are beneficial) from noisy samples (which are harmful). To bridge this gap, we propose the joint Federated Meta-Weighting based Client and Sample Selection (FedMW-CSS) approach to simultaneously mitigate label noise and hard sample selection. It is a bilevel optimization approach for FL client-and-sample selection and global model construction to achieve hard sample-aware noise-robust learning in a privacy preserving manner. It performs meta-learning based online approximation to iteratively update global FL models, select the most positively influential samples and deal with training data noise. To utilize both the instance-level information and class-level information for better performance improvements, FedMW-CSS efficiently learns a class-level weight by manipulating gradients at the class level, e.g., it performs a gradient descent step on class-level weights, which only relies on intermediate gradients. Theoretically, we analyze the privacy guarantees and convergence of FedMW-CSS. Extensive experiments comparison against eight state-of-the-art baselines on six real-world datasets in the presence of data noise and heterogeneity shows that FedMW-CSS achieves up to 28.5% higher test accuracy, while saving communication and computation costs by at least 49.3% and 1.2%, respectively.

Similar Papers
  • Research Article
  • Citations392

Convergence Time Optimization for Federated Learning Over Wireless Networks

  • Dec 11, 2020
  • IEEE Transactions on Wireless Communications
  • Mingzhe Chen +3
  • Conference Article
  • Citations14

Health Risk Assessment with Federated Learning

  • Aug 22, 2022
  • Ioanna Diamantoulaki +4
  • Research Article

Federated Deep Learning Approaches for Detecting Ocular Diseases in Medical Imaging: A Systematic Review.

  • Nov 01, 2025
  • Current medical imaging
  • Seema Gulati +3
  • Research Article
  • Citations97

Effectiveness of Federated Learning and CNN Ensemble Architectures for Identifying Brain Tumors Using MRI Images

  • Aug 28, 2022
  • Neural Processing Letters
  • Moinul Islam +3
  • Conference Article
  • Citations1

Privacy-Preserving Federated Learning via Disentanglement

  • Oct 21, 2023
  • Wenjie Zhou +6
  • Research Article

Strategic Optimization of Convergence and Energy in Federated Learning Systems

  • Jan 01, 2025
  • The International Arab Journal of Information Technology
  • Ghassan Samara +8
  • Research Article
  • Citations4

Secure Extraction of Personal Information from EHR by Federated Machine Learning.

  • Aug 22, 2024
  • Studies in health technology and informatics
  • Mohamed El Azzouzi +4
  • Research Article
  • Citations4

FedBeam: Reliable Incentive Mechanisms for Federated Learning in UAV-Enabled Internet of Vehicles

  • Oct 10, 2024
  • Drones
  • Gangqiang Hu +5
  • Research Article
  • Citations19

Methods and Impact for Using Federated Learning to Collaborate on Clinical Research.

  • Nov 08, 2022
  • Neurosurgery
  • Alexander T M Cheung +18
  • Research Article
  • Citations4

Dynamic Pricing for Client Recruitment in Federated Learning

  • Apr 01, 2024
  • IEEE/ACM Transactions on Networking
  • Xuehe Wang +2
  • Research Article
  • Citations3

Joint learning and optimization for Federated Learning in NOMA-based networks

  • Dec 27, 2022
  • Pervasive and Mobile Computing
  • Ilyes Mrad +3
  • Research Article
  • Citations61

Lightweight Federated Learning for Rice Leaf Disease Classification Using Non Independent and Identically Distributed Images

  • Aug 09, 2023
  • Sustainability
  • Meenakshi Aggarwal +5
  • Research Article
  • Citations44

WiFederated: Scalable WiFi Sensing Using Edge-Based Federated Learning

  • Jul 15, 2022
  • IEEE Internet of Things Journal
  • Steven M Hernandez +1
  • Research Article

Federated transfer learning-based intrusion detection system in 5G networks

  • Apr 01, 2026
  • Expert Systems with Applications
  • Andrea Bellmunt +3
  • Research Article
  • Citations4

FedMarket: A Cryptocurrency Driven Marketplace for Mobile Federated Learning Services

  • Jan 01, 2022
  • IEEE Access
  • Abdullah Yousafzai +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.