mlsanityData to 7 Oct 2026

FedPSA: Modeling Behavioral Staleness in Asynchronous Federated Learning

arXiv 2602.15337 ↗First posted 17 Feb 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Asynchronous Federated Learning (AFL) has emerged as a significant research area in recent years. By not waiting for slower clients and executing the training process concurrently, it achieves faster training speed compared to traditional federated learning. However, due to the staleness introduced by the asynchronous process, its performance may degrade in some scenarios. Existing methods often use the round difference between the current model and the global model as the sole measure of staleness, which is coarse-grained and lacks observation of the model itself, thereby limiting the performance ceiling of asynchronous methods. In this paper, we propose FedPSA (Parameter Sensitivity-based Asynchronous Federated Learning), a more fine-grained AFL framework that leverages parameter sensitivity to measure model obsolescence and establishes a dynamic momentum queue to assess the current training phase in real time, thereby adjusting the tolerance for outdated information dynamically. Extensive experiments on multiple datasets and comparisons with various methods demonstrate the superior performance of FedPSA, achieving up to 6.37% improvement over baseline methods and 1.93% over the current state-of-the-art method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 50 references that are in the map. First posted on arXiv 17 Feb 2026.

Builds on

23 of 50 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  6. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
  7. 2019Importance Estimation for Neural Network Pruningcited by 531
  8. 2015An Introduction to Convolutional Neural Networkscited by 510
  9. 2019Asynchronous Federated Optimizationcited by 264
  10. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
  11. 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
  12. 2019SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overheadcited by 82
11 more
  1. 2021FedCM: Federated Learning with Client-level Momentumcited by 77
  2. 2023FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Updatecited by 32
  3. 2023TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Trainingcited by 27
  4. 2023Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaborationcited by 23
  5. 2024Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysiscited by 21
  6. 2023FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropoutcited by 16
  7. 2023FLGo: A Fully Customizable Federated Learning Platformcited by 12
  8. 2024FedFa: A Fully Asynchronous Training Paradigm for Federated Learningcited by 12
  9. 2024Momentum Approximation in Asynchronous Private Federated Learningcited by 3
  10. 2025AFBS:Buffer Gradient Selection in Semi-asynchronous Federated Learningcited by 2
  11. 2024Asyn2F: An Asynchronous Federated Learning Framework with Bidirectional Model Aggregationcited by 1

Built on by

Not cited yet.