FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update

Authors: Ji Liu, Juncheng Jia, Tianshi Che, Chao Huo, Jiaxiang Ren, Yang Zhou, Huaiyu Dai, Dejing Dou

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimentation with 6 models and 5 public datasets demonstrates that Fed ASMU significantly outperforms baseline approaches in terms of accuracy (0.60% to 23.90% higher) and efficiency (3.54% to 97.98% faster).
Researcher Affiliation Collaboration Ji Liu1* Juncheng Jia2,3 , Tianshi Che4, Chao Huo2, Jiaxiang Ren4, Yang Zhou4, Huaiyu Dai5, Dejing Dou6 1 Hithink Royal Flush Information Network Co., Ltd., China. 2 Soochow University, China 3 Collaborative Innovation Center of Novel Software Technology and Industrialization, China 4 Auburn University, United States 5 North Carolina State University, United States 6 Boston Consulting Group, China
Pseudocode Yes Algorithm 1: Fed ASMU on the Server and Algorithm 2: Fed ASMU on Devices are provided.
Open Source Code No The paper does not include any explicit statements about releasing source code for the described methodology, nor does it provide a direct link to a code repository.
Open Datasets Yes We utilize 5 public datasets, i.e., Fashion-MNIST (FMNSIT) (Xiao, Rasul, and Vollgraf 2017), CIFAR-10 and CIFAR-100 (Krizhevsky, Hinton et al. 2009), IMDb (Zhou et al. 2021b), and Tiny-Image Net (Le and Yang 2015).
Dataset Splits No The paper mentions using a Dirichlet distribution for non-IID data but does not specify exact training, validation, and test dataset splits (e.g., percentages or specific sample counts) or cross-validation setup.
Hardware Specification No The paper does not specify any particular hardware components (e.g., GPU models, CPU models, or memory) used for running the experiments.
Software Dependencies No The paper does not provide specific version numbers for any software dependencies, such as programming languages, libraries, or frameworks.
Experiment Setup No While the paper mentions the existence of hyperparameters and describes certain processes (like SGD), it does not provide concrete values for hyperparameters (e.g., learning rate, batch size, number of epochs) or other detailed system-level training settings needed for reproduction.