FedMut: Generalized Federated Learning via Stochastic Mutation

Authors: Ming Hu, Yue Cao, Anran Li, Zhiming Li, Chengwei Liu, Tianlin Li, Mingsong Chen, Yang Liu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on well-known datasets demonstrate the effectiveness of our Fed Mut approach in various data heterogeneity scenarios.
Researcher Affiliation Academia 1School of Computer Science and Engineering, Nanyang Technological University, Singapore 2Mo E Engineering Research Center of SW/HW Co-Design Tech. and App., East China Normal University, China
Pseudocode Yes Algorithm 1: Implementation of Fed Mut
Open Source Code No The paper does not provide an explicit statement or link for the open-sourcing of its own code.
Open Datasets Yes We selected three well-known datasets to evaluate the effectiveness of our Fed Mut approach, i.e., CIFAR-10, CIFAR-100 (Krizhevsky 2009), and Shakespeare (Caldas et al. 2018), respectively, where CIFAR-10 and CIFAR-100 are image datasets and Shakespeare is a text dataset.
Dataset Splits No The paper describes training and testing, but it does not explicitly specify a validation dataset split or its size/percentage.
Hardware Specification Yes We conducted all the experiments on an Ubuntu workstation with an Intel i9 CPU, 64GB memory, and two NVIDIA RTX 4090 GPUs.
Software Dependencies No The paper mentions software components like 'SGD optimizer' and models like 'Res Net-18' and 'VGG16 (Torchvision Model 2022)', but does not specify versions for programming languages or libraries (e.g., Python, PyTorch).
Experiment Setup Yes For all the experiments, we set SGD optimizer with a learning rate of 0.01 and a momentum of 0.9. For each FL training round, we set the batch size to 50 and the number epoch of each local training to 5.