mlsanityData to 14 Oct 2026

Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating

arXiv 1910.08234 ↗First posted 18 Oct 2019cs.LG cs.DC stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) aims to train machine learning models in the decentralized system consisting of an enormous amount of smart edge devices. Federated averaging (FedAvg), the fundamental algorithm in FL settings, proposes on-device training and model aggregation to avoid the potential heavy communication costs and privacy concerns brought by transmitting raw data. However, through theoretical analysis we argue that 1) the multiple steps of local updating will result in gradient biases and 2) there is an inconsistency between the expected target distribution and the optimization objectives following the training paradigm in FedAvg. To tackle these problems, we first propose an unbiased gradient aggregation algorithm with the keep-trace gradient descent and the gradient evaluation strategy. Then we introduce an additional controllable meta updating procedure with a small set of data samples, indicating the expected target distribution, to provide a clear and consistent optimization objective. Both the two improvements are model- and task-agnostic and can be applied individually or together. Experimental results demonstrate that the proposed methods are faster in convergence and achieve higher accuracy with different network architectures in various FL settings.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 8; 2023: 2; 2024: 3; 2025: 2.

22 papers.

Sort:

By area:

  1. 2022On the Importance and Applicability of Pre-Training for Federated Learningcited by 71
  2. 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
  3. 2021Gradient-Leakage Resilient Federated Learningcited by 40
  4. 2021Emerging Trends in Federated Learning: From Model Fusion to Federated X Learningcited by 35
  5. 2022Data Heterogeneity-Robust Federated Learning via Group Client Selection in Industrial IoTcited by 25
  6. 2021Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identificationcited by 20
  7. 2021On Bridging Generic and Personalized Federated Learning for Image Classificationcited by 15
  8. 2022Continual Learning for Peer-to-Peer Federated Learning: A Study on Automated Brain Metastasis Identificationcited by 13
  9. 2022Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysiscited by 9
  10. 2022Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Trainingcited by 7
  11. 2024MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classescited by 7
  12. 2022Metrizing Fairnesscited by 6
10 more
  1. 2021Aggregate or Not? Exploring Where to Privatize in DNN Based Federated Learning Under Different Non-IID Scenescited by 4
  2. 2022Personalized Federated Learning with Exact Stochastic Gradient Descentcited by 4
  3. 2021Gradient Masked Federated Optimizationcited by 2
  4. 2023FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularizationcited by 2
  5. 2024Gradient-Congruity Guided Federated Sparse Trainingcited by 2
  6. 2021Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasetscited by 1
  7. 2024Data Poisoning and Leakage Analysis in Federated Learningcited by 1
  8. 2023Leveraging Learning Metrics for Improved Federated Learningcited by 0
  9. 2025Traversal Learning: A Lossless And Efficient Distributed Learning Frameworkcited by 0
  10. 2025FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learningcited by 0