H-FL: A Hierarchical Communication-Efficient and Privacy-Protected Architecture for Federated Learning

Authors: He Yang

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that our H-FL framework achieves the state-of-art performance on different datasets for the real-world image recognition tasks. We evaluate H-FL on different datasets and compare the performance to Fed AVG [Mc Mahan et al., 2017a], STC [Sattler et al., 2019] and DGC [Lin et al., 2018] in non-IID environments.
Researcher Affiliation Academia Xi an Jiaotong University sleepingcat@stu.xjtu.edu.cn
Pseudocode Yes Algorithm 1 Runtime distribution reconstruction; Algorithm 2 The workflow for H-FL
Open Source Code No The paper does not provide any statement or link regarding the availability of its source code.
Open Datasets Yes Specifically, we have trained a modified version of Le Net5 [Le Cun et al., 1998] network on FMNIST [Xiao et al., 2017] and a modified VGG16 [Simonyan and Zisserman, 2014] network network on CIFAR10 [Krizhevsky et al., 2009] respectively.
Dataset Splits No The paper does not provide specific train/validation/test dataset splits (percentages or sample counts). It only mentions using FMNIST and CIFAR10 in non-IID environments.
Hardware Specification No The paper does not mention any specific hardware details such as GPU models, CPU types, or memory specifications used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes The experiment settings are listed in Table 2. Dataset Clients Mediators η classes per client I L CIFAR10 100 3 0.015 3 10 1 FMNIST 100 3 0.015 2 10 1