mlsanityData to 7 Oct 2026

Fast-Convergent Federated Learning with Adaptive Weighting

arXiv 2012.00661 ↗First posted 1 Dec 2020cs.LG cs.AIcited by 67

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables resource-constrained edge nodes to collaboratively learn a global model under the orchestration of a central server while keeping privacy-sensitive data locally. The non-independent-and-identically-distributed (non-IID) data samples across participating nodes slow model training and impose additional communication rounds for FL to converge. In this paper, we propose Federated Adaptive Weighting (FedAdp) algorithm that aims to accelerate model convergence under the presence of nodes with non-IID dataset. We observe the implicit connection between the node contribution to the global model aggregation and data distribution on the local node through theoretical and empirical analysis. We then propose to assign different weights for updating the global model based on node contribution adaptively through each training round. The contribution of participating nodes is first measured by the angle between the local gradient vector and the global gradient vector, and then, weight is quantified by a designed non-linear mapping function subsequently. The simple yet effective strategy can reinforce positive (suppress negative) node contribution dynamically, resulting in communication round reduction drastically. Its superiority over the commonly adopted Federated Averaging (FedAvg) is verified both theoretically and experimentally. With extensive experiments performed in Pytorch and PySyft, we show that FL training with FedAdp can reduce the number of communication rounds by up to 54.1% on MNIST dataset and up to 45.4% on FashionMNIST dataset, as compared to FedAvg algorithm.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 9; 2023: 13; 2024: 16; 2025: 16; 2026: 9.

67 papers.

Sort:

By area:

  1. 2021Node Selection Toward Faster Convergence for Federated Learning on Non-IID Datacited by 39
  2. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  3. 2022Accelerated Federated Learning with Decoupled Adaptive Optimizationcited by 23
  4. 2021Prototype Guided Federated Learning of Visual Feature Representationscited by 22
  5. 2025Can Textual Gradient Work in Federated Learning?cited by 14
  6. 2024Task Arithmetic Through The Lens Of One-Shot Federated Learningcited by 12
  7. 2021Federated Face Recognitioncited by 9
  8. 2023Federated Recommendation with Additive Personalizationcited by 9
  9. 2024Fast-Convergent and Communication-Alleviated Heterogeneous Hierarchical Federated Learning in Autonomous Drivingcited by 8
  10. 2022FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learningcited by 7
  11. 2025Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocationcited by 7
  12. 2022Federated Learning on Adaptively Weighted Nodes by Bilevel Optimizationcited by 6
38 more
  1. 2022Federated Learning with Server Learning: Enhancing Performance for Non-IID Datacited by 6
  2. 2023CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled Regularizationcited by 5
  3. 2023Federated Skewed Label Learning with Logits Fusioncited by 5
  4. 2024Blockchain-enabled Trustworthy Federated Unlearningcited by 5
  5. 2025A Thorough Assessment of the Non-IID Data Impact in Federated Learningcited by 5
  6. 2022Matching DNN Compression and Cooperative Training with Resources and Data Availabilitycited by 4
  7. 2022Efficient Fully Distributed Federated Learning with Adaptive Local Linkscited by 3
  8. 2023Adaptive Federated Learning via New Entropy Approachcited by 3
  9. 2023Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applicationscited by 3
  10. 2023FedCode: Communication-Efficient Federated Learning via Transferring Codebookscited by 3
  11. 2024An Element-Wise Weights Aggregation Method for Federated Learningcited by 3
  12. 2024On the Impact of Data Heterogeneity in Federated Learning Environments with Application to Healthcare Networkscited by 3
  13. 2024Optimizing Federated Learning by Entropy-Based Client Selectioncited by 3
  14. 2022FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneitycited by 2
  15. 2023A Federated Learning Benchmark for Drug-Target Interactioncited by 2
  16. 2023Straggler-resilient Federated Learning: Tackling Computation Heterogeneity with Layer-wise Partial Model Training in Mobile Edge Networkcited by 2
  17. 2024Towards Fair, Robust and Efficient Client Contribution Evaluation in Federated Learningcited by 2
  18. 2024SignSGD with Federated Votingcited by 2
  19. 2024Gradients Stand-in for Defending Deep Leakage in Federated Learningcited by 2
  20. 2022Improving the Robustness of Federated Learning for Severely Imbalanced Datasetscited by 1
  21. 2023Federated Learning Model Aggregation in Heterogenous Aerial and Space Networkscited by 1
  22. 2023A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averagingcited by 1
  23. 2023PAGE: Equilibrate Personalization and Generalization in Federated Learningcited by 1
  24. 2024SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decodingcited by 1
  25. 2024Federated Learning Can Find Friends That Are Advantageouscited by 1
  26. 2024Context-Aware Orchestration of Energy-Efficient Gossip Learning Schemescited by 1
  27. 2024Dual-Segment Clustering Strategy for Hierarchical Federated Learning in Heterogeneous Wireless Environmentscited by 1
  28. 2024Low-Resource Machine Translation through the Lens of Personalized Federated Learningcited by 1
  29. 2025The Impact Analysis of Delays in Asynchronous Federated Learning with Data Heterogeneity for Edge Intelligencecited by 1
  30. 2025Adaptive Deadline and Batch Layered Synchronized Federated Learningcited by 1
  31. 2025Detect & Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learningcited by 1
  32. 2025On the Fragility of Contribution Score Computation in Federated Learningcited by 1
  33. 2025CATCHFed: Efficient Unlabeled Data Utilization for Semi-Supervised Federated Learning in Limited Labels Environmentscited by 1
  34. 2026Private and Robust Contribution Evaluation in Federated Learningcited by 1
  35. 2022Deep Unfolding-based Weighted Averaging for Federated Learning in Heterogeneous Environmentscited by 0
  36. 2023When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learningcited by 0
  37. 2023FedAgg: Adaptive Federated Learning with Aggregated Gradientscited by 0
  38. 2024Dependable Distributed Training of Compressed Machine Learning Modelscited by 0

50 most cited of 67 All 67 (JSON)