FedDWA: Personalized Federated Learning with Dynamic Weight Adjustment

Authors: Jiahao Liu, Jiang Wu, Jinyu Chen, Miao Hu, Yipeng Zhou, Di Wu

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we conduct extensive experiments using five real datasets and the results demonstrate that Fed DWA can significantly reduce the communication traffic and achieve much higher model accuracy than the state-of-the-art approaches.
Researcher Affiliation Academia 1School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China 2Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China 3School of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, Australia
Pseudocode Yes Algorithm 1 Fed DWA algorithm
Open Source Code No The paper does not provide a direct link to open-source code for the described methodology or state that the code is publicly available. It only links to an extended version of the paper on arXiv.
Open Datasets Yes We evaluate our algorithm on five benchmark datasets, namely, EMNIST [Cohen et al., 2017], CIFAR10, CIFAR100 [Krizhevsky et al., 2009], CINIC10 [Darlow et al., 2018] and Tiny-Image Net (TINY) [Chrabaszcz et al., 2017].
Dataset Splits No The paper describes data partitioning for client heterogeneity (e.g., s% of data from dominant classes, Dirichlet distribution) and mentions evaluation metrics, but it does not explicitly describe a validation dataset split (e.g., percentages or counts) used for hyperparameter tuning or model selection during training for its own method.
Hardware Specification No The paper does not specify any particular hardware used for running the experiments (e.g., specific GPU or CPU models, memory details).
Software Dependencies No The paper mentions using specific models (e.g., CNN, ResNet-8) and optimizers (mini-batch SGD), but it does not provide version numbers for any software dependencies like programming languages, frameworks (e.g., PyTorch, TensorFlow), or libraries.
Experiment Setup Yes The number of local training epochs is set to E = 1 and the number of global communication rounds is set to 100. We employ the mini-batch SGD as a local optimizer for all approaches. The batch size for each client is set as 20 and the learning rate η is set as 0.01.