# Optimal Importance Sampling for Federated Learning

arXiv: https://arxiv.org/abs/2010.13600 · HTML: https://mlsanity.com/paper/2010.13600/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2020.

## Built on by (most cited first, 20 of 20)

- [Client Selection in Federated Learning: Principles, Challenges, and Opportunities](https://mlsanity.com/paper/2211.01549/) (2022)
- [Node Selection Toward Faster Convergence for Federated Learning on Non-IID Data](https://mlsanity.com/paper/2105.07066/) (2021)
- [Communication-Efficient Online Federated Learning Framework for Nonlinear Regression](https://mlsanity.com/paper/2110.06556/) (2021)
- [Green Federated Learning: A new era of Green Aware AI](https://mlsanity.com/paper/2409.12626/) (2024)
- [A Graph Federated Architecture with Privacy Preserving Learning](https://mlsanity.com/paper/2104.13215/) (2021)
- [Fast Heterogeneous Federated Learning with Hybrid Client Selection](https://mlsanity.com/paper/2208.05135/) (2022)
- [Greedy Shapley Client Selection for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2312.09108/) (2023)
- [Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange](https://mlsanity.com/paper/2208.02856/) (2022)
- [ISFL: Federated Learning for Non-i.i.d. Data with Local Importance Sampling](https://mlsanity.com/paper/2210.02119/) (2022)
- [Variance-Reduced Heterogeneous Federated Learning via Stratified Client Selection](https://mlsanity.com/paper/2201.05762/) (2022)
- [Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning](https://mlsanity.com/paper/2212.09483/) (2022)
- [Accelerating Federated Edge Learning via Optimized Probabilistic Device Scheduling](https://mlsanity.com/paper/2107.11588/) (2021)
- [Data Games: A Game-Theoretic Approach to Swarm Robotic Data Collection](https://mlsanity.com/paper/2303.03602/) (2023)
- [LEFL: Low Entropy Client Sampling in Federated Learning](https://mlsanity.com/paper/2312.17430/) (2023)
- [Histogram-Based Federated XGBoost using Minimal Variance Sampling for Federated Tabular Data](https://mlsanity.com/paper/2405.02067/) (2024)
- [FedAVOT: Exact Distribution Alignment in Federated Learning via Masked Optimal Transport](https://mlsanity.com/paper/2509.14444/) (2025)
- [Uplink Scheduling in Federated Learning: an Importance-Aware Approach via Graph Representation Learning](https://mlsanity.com/paper/2301.11903/) (2023)
- [Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels](https://mlsanity.com/paper/2404.09861/) (2024)
- [FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learning](https://mlsanity.com/paper/2509.13895/) (2025)
- [FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching](https://mlsanity.com/paper/2606.10124/) (2026)

## 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.