mlsanityData to 14 Oct 2026

Client Selection in Federated Learning based on Gradients Importance

arXiv 2111.11204 ↗First posted 19 Nov 2021cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables multiple devices to collaboratively learn a global model without sharing their personal data. In real-world applications, the different parties are likely to have heterogeneous data distribution and limited communication bandwidth. In this paper, we are interested in improving the communication efficiency of FL systems. We investigate and design a device selection strategy based on the importance of the gradient norms. In particular, our approach consists of selecting devices with the highest norms of gradient values at each communication round. We study the convergence and the performance of such a selection technique and compare it to existing ones. We perform several experiments with non-iid set-up. The results show the convergence of our method with a considerable increase of test accuracy comparing to the random selection.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 11 of its 16 references that are in the map. First posted on arXiv 19 Nov 2021.

Builds on

11 of 16 references.

References · 11

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  4. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  5. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
  6. 2017Sparse Communication for Distributed Gradient Descentcited by 249
  7. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
  8. 2020Towards Flexible Device Participation in Federated Learningcited by 65
  9. 2020Communication-Efficient Federated Learning via Optimal Client Samplingcited by 39
  10. 2019On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learningcited by 32
  11. 2019Stochastic Three Points Method for Unconstrained Smooth Minimizationcited by 24

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 5; 2026: 2.

9 papers.

  1. 2023Client Selection for Federated Policy Optimization with Environment Heterogeneitycited by 3
  2. 2025AdRo-FL: Informed and Secure Client Selection for Federated Learning in the Presence of Adversarial Aggregatorcited by 1
  3. 2024Fast networked data selection via distributed smoothed quantile estimationcited by 0
  4. 2025XAI-Driven Client Selection for Federated Learning in Scalable 6G Network Slicingcited by 0
  5. 2025PNCS:Power-Norm Cosine Similarity for Diverse Client Selection in Federated Learningcited by 0
  6. 2025Long-Term Client Selection for Federated Learning with Non-IID Data: A Truthful Auction Approachcited by 0
  7. 2025FairEnergy: Contribution-Based Fairness meets Energy Efficiency in Federated Learningcited by 0
  8. 2026SCOPE-FL: A Strategy-proof Chain-based Optimal pareto efficient Federated Learning Systemcited by 0
  9. 2026Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learningcited by 0