mlsanityData to 7 Oct 2026

FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting

arXiv 2608.14654 ↗First posted 31 Jul 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a collaborative paradigm that enables multiple devices to train a global model while preserving local data privacy. A major challenge in FL is the non-Independent and Identically Distributed (non-IID) nature of data across devices, which hinders training efficiency and slows convergence. To tackle this, we propose Federated Impurity Weighting (FedImp), a novel algorithm that quantifies each device contribution based on the informational content of its local data. These contributions are normalized to compute distinct aggregation weights for the global model update. Extensive experiments on EMNIST and CIFAR-10 datasets show that FedImp significantly improves convergence speed, reducing communication rounds by up to 64.4%, 27.8%, and 66.7% on EMNIST, and 44.2%, 44%, and 25.6% on CIFAR-10 compared to FedAvg, FedProx, and FedAdp, respectively. Under highly imbalanced data distributions, FedImp outperforms all baselines and achieves the highest accuracy. Overall, FedImp offers an effective solution to enhance FL efficiency in non-IID settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 22 references that are in the map. First posted on arXiv 31 Jul 2026.

Builds on

14 of 22 references.

References · 14

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2020Adaptive Federated Optimizationcited by 1,036
  5. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  6. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  7. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  8. 2021Federated Learning: Opportunities and Challengescited by 83
  9. 2020Fast-Convergent Federated Learning with Adaptive Weightingcited by 67
  10. 2020Inverse Distance Aggregation for Federated Learning with Non-IID Datacited by 44
  11. 2021Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneitycited by 27
  12. 2020A Systematic Literature Review on Federated Learning: From A Model Quality Perspectivecited by 15
2 more
  1. 2025Decentralized and Robust Privacy-Preserving Model Using Blockchain-Enabled Federated Deep Learning in Intelligent Enterprisescited by 7
  2. 2025A Lightweight and Secure Deep Learning Model for Privacy-Preserving Federated Learning in Intelligent Enterprisescited by 5

Built on by

Not cited yet.