mlsanityData to 7 Oct 2026

Optimal Importance Sampling for Federated Learning

arXiv 2010.13600 ↗First posted 26 Oct 2020cs.LG cs.DCcited by 20

Not on the map. Why?

Abstract (arXiv)

Federated learning involves a mixture of centralized and decentralized processing tasks, where a server regularly selects a sample of the agents and these in turn sample their local data to compute stochastic gradients for their learning updates. This process runs continually. The sampling of both agents and data is generally uniform; however, in this work we consider non-uniform sampling. We derive optimal importance sampling strategies for both agent and data selection and show that non-uniform sampling without replacement improves the performance of the original FedAvg algorithm. We run experiments on a regression and classification problem to illustrate the theoretical results.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 4; 2024: 3; 2025: 2; 2026: 1.

20 papers.

Sort:

  1. 2022Client Selection in Federated Learning: Principles, Challenges, and Opportunitiescited by 62
  2. 2021Node Selection Toward Faster Convergence for Federated Learning on Non-IID Datacited by 39
  3. 2021Communication-Efficient Online Federated Learning Framework for Nonlinear Regressioncited by 16
  4. 2024Green Federated Learning: A new era of Green Aware AIcited by 12
  5. 2021A Graph Federated Architecture with Privacy Preserving Learningcited by 10
  6. 2022Fast Heterogeneous Federated Learning with Hybrid Client Selectioncited by 8
  7. 2023Greedy Shapley Client Selection for Communication-Efficient Federated Learningcited by 6
  8. 2022Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchangecited by 5
  9. 2022ISFL: Federated Learning for Non-i.i.d. Data with Local Importance Samplingcited by 4
  10. 2022Variance-Reduced Heterogeneous Federated Learning via Stratified Client Selectioncited by 3
  11. 2022Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learningcited by 3
  12. 2021Accelerating Federated Edge Learning via Optimized Probabilistic Device Schedulingcited by 2
8 more
  1. 2023Data Games: A Game-Theoretic Approach to Swarm Robotic Data Collectioncited by 1
  2. 2023LEFL: Low Entropy Client Sampling in Federated Learningcited by 1
  3. 2024Histogram-Based Federated XGBoost using Minimal Variance Sampling for Federated Tabular Datacited by 1
  4. 2025FedAVOT: Exact Distribution Alignment in Federated Learning via Masked Optimal Transportcited by 1
  5. 2023Uplink Scheduling in Federated Learning: an Importance-Aware Approach via Graph Representation Learningcited by 0
  6. 2024Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labelscited by 0
  7. 2025FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learningcited by 0
  8. 2026FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Cachingcited by 0