# Active Federated Learning

arXiv: https://arxiv.org/abs/1909.12641 · HTML: https://mlsanity.com/paper/1909.12641/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2019.

## Built on by (most cited first, 30 of 63)

- [Towards Building the Federated GPT: Federated Instruction Tuning](https://mlsanity.com/paper/2305.05644/) (2023)
- [On Large-Cohort Training for Federated Learning](https://mlsanity.com/paper/2106.07820/) (2021)
- [Towards Fairness-Aware Federated Learning](https://mlsanity.com/paper/2111.01872/) (2021)
- [FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning](https://mlsanity.com/paper/2103.13822/) (2021)
- [Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction](https://mlsanity.com/paper/2209.15245/) (2022)
- [On the Convergence of Federated Averaging with Cyclic Client Participation](https://mlsanity.com/paper/2302.03109/) (2023)
- [Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimization](https://mlsanity.com/paper/2201.07912/) (2022)
- [FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems](https://mlsanity.com/paper/2104.07515/) (2021)
- [Knowledge-Aware Federated Active Learning with Non-IID Data](https://mlsanity.com/paper/2211.13579/) (2022)
- [On the Role of Server Momentum in Federated Learning](https://mlsanity.com/paper/2312.12670/) (2023)
- [FedImpro: Measuring and Improving Client Update in Federated Learning](https://mlsanity.com/paper/2402.07011/) (2024)
- [Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network](https://mlsanity.com/paper/2208.12044/) (2022)
- [Exploiting Label Skews in Federated Learning with Model Concatenation](https://mlsanity.com/paper/2312.06290/) (2023)
- [A Survey on Class Imbalance in Federated Learning](https://mlsanity.com/paper/2303.11673/) (2023)
- [From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samples](https://mlsanity.com/paper/2512.19363/) (2025)
- [Towards Interpretable Federated Learning](https://mlsanity.com/paper/2302.13473/) (2023)
- [A Snapshot of the Frontiers of Client Selection in Federated Learning](https://mlsanity.com/paper/2210.04607/) (2022)
- [FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-based Optimization](https://mlsanity.com/paper/2405.06312/) (2024)
- [Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learning](https://mlsanity.com/paper/2106.10734/) (2021)
- [Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection](https://mlsanity.com/paper/2109.04253/) (2021)
- [FedDebug: Systematic Debugging for Federated Learning Applications](https://mlsanity.com/paper/2301.03553/) (2023)
- [A Comprehensive Survey On Client Selections in Federated Learning](https://mlsanity.com/paper/2311.06801/) (2023)
- [Sustainable Federated Learning](https://mlsanity.com/paper/2102.11274/) (2021)
- [FedFair^3: Unlocking Threefold Fairness in Federated Learning](https://mlsanity.com/paper/2401.16350/) (2024)
- [FedMint: Intelligent Bilateral Client Selection in Federated Learning with Newcomer IoT Devices](https://mlsanity.com/paper/2211.01805/) (2022)
- [Privacy-preserving and Uncertainty-aware Federated Trajectory Prediction for Connected Autonomous Vehicles](https://mlsanity.com/paper/2303.04340/) (2023)
- [FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant Clients](https://mlsanity.com/paper/2411.01825/) (2024)
- [Online Meta-Learning for Model Update Aggregation in Federated Learning for Click-Through Rate Prediction](https://mlsanity.com/paper/2209.00629/) (2022)
- [Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning](https://mlsanity.com/paper/2310.00198/) (2023)
- [Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning](https://mlsanity.com/paper/2405.04122/) (2024)

## Abstract (arXiv)

Federated Learning allows for population level models to be trained without centralizing client data by transmitting the global model to clients, calculating gradients locally, then averaging the gradients. Downloading models and uploading gradients uses the client's bandwidth, so minimizing these transmission costs is important. The data on each client is highly variable, so the benefit of training on different clients may differ dramatically. To exploit this we propose Active Federated Learning, where in each round clients are selected not uniformly at random, but with a probability conditioned on the current model and the data on the client to maximize efficiency. We propose a cheap, simple and intuitive sampling scheme which reduces the number of required training iterations by 20-70% while maintaining the same model accuracy, and which mimics well known resampling techniques under certain conditions.