# FedADC: Accelerated Federated Learning with Drift Control

arXiv: https://arxiv.org/abs/2012.09102 · HTML: https://mlsanity.com/paper/2012.09102/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2020.

## Built on by (most cited first, 26 of 26)

- [FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy](https://mlsanity.com/paper/2302.10429/) (2023)
- [Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape](https://mlsanity.com/paper/2305.11584/) (2023)
- [Time-Correlated Sparsification for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2101.08837/) (2021)
- [Communication-Efficient Federated Learning with Accelerated Client Gradient](https://mlsanity.com/paper/2201.03172/) (2022)
- [Accelerated Federated Learning with Decoupled Adaptive Optimization](https://mlsanity.com/paper/2207.07223/) (2022)
- [Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup](https://mlsanity.com/paper/2308.00522/) (2023)
- [Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization](https://mlsanity.com/paper/2306.05706/) (2023)
- [Vertical Federated Learning: A Structured Literature Review](https://mlsanity.com/paper/2212.00622/) (2022)
- [Federated Continual Learning: Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2502.07059/) (2025)
- [Accelerating Heterogeneous Federated Learning with Closed-form Classifiers](https://mlsanity.com/paper/2406.01116/) (2024)
- [Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning](https://mlsanity.com/paper/2310.01366/) (2023)
- [Hierarchical Federated Learning with Momentum Acceleration in Multi-Tier Networks](https://mlsanity.com/paper/2210.14560/) (2022)
- [Resource-Aware Asynchronous Online Federated Learning for Nonlinear Regression](https://mlsanity.com/paper/2111.13931/) (2021)
- [FilFL: Client Filtering for Optimized Client Participation in Federated Learning](https://mlsanity.com/paper/2302.06599/) (2023)
- [Stabilizing and Improving Federated Learning with Non-IID Data and Client Dropout](https://mlsanity.com/paper/2303.06314/) (2023)
- [Communication-Efficient Heterogeneous Federated Learning with Generalized Heavy-Ball Momentum](https://mlsanity.com/paper/2311.18578/) (2023)
- [Momentum Approximation in Asynchronous Private Federated Learning](https://mlsanity.com/paper/2402.09247/) (2024)
- [Federated Spatial Reuse Optimization in Next-Generation Decentralized IEEE 802.11 WLANs](https://mlsanity.com/paper/2203.10472/) (2022)
- [Federated Learning for Non-IID Data via Client Variance Reduction and Adaptive Server Update](https://mlsanity.com/paper/2207.08391/) (2022)
- [Asynchronous Online Federated Learning with Reduced Communication Requirements](https://mlsanity.com/paper/2303.15226/) (2023)
- [A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs](https://mlsanity.com/paper/2409.18915/) (2024)
- [Addressing Data Heterogeneity in Decentralized Learning via Topological Pre-processing](https://mlsanity.com/paper/2212.08743/) (2022)
- [Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning](https://mlsanity.com/paper/2404.06230/) (2024)
- [On the Limits of Momentum in Decentralized and Federated Optimization](https://mlsanity.com/paper/2511.20168/) (2025)
- [Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization](https://mlsanity.com/paper/2604.12768/) (2026)
- [FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity](https://mlsanity.com/paper/2607.03763/) (2026)

## Abstract (arXiv)

Federated learning (FL) has become de facto framework for collaborative learning among edge devices with privacy concern. The core of the FL strategy is the use of stochastic gradient descent (SGD) in a distributed manner. Large scale implementation of FL brings new challenges, such as the incorporation of acceleration techniques designed for SGD into the distributed setting, and mitigation of the drift problem due to non-homogeneous distribution of local datasets. These two problems have been separately studied in the literature; whereas, in this paper, we show that it is possible to address both problems using a single strategy without any major alteration to the FL framework, or introducing additional computation and communication load. To achieve this goal, we propose FedADC, which is an accelerated FL algorithm with drift control. We empirically illustrate the advantages of FedADC.