Sparse Random Networks for Communication-Efficient Federated Learning

Authors: Berivan Isik, Francesco Pase, Deniz Gunduz, Tsachy Weissman, Zorzi Michele

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

Reproducibility Variable Result LLM Response
Research Type Experimental We show improvements in accuracy, communication (less than 1 bit per parameter (bpp)), convergence speed, and final model size (less than 1 bpp) over relevant baselines on MNIST, EMNIST, CIFAR10, and CIFAR-100 datasets, in the low bitrate regime. In this section, we empirically show the performance of Fed PM in terms of accuracy, bitrate, converge speed, and the final model size.
Researcher Affiliation Academia Stanford University, University of Padova, Imperial College London berivan.isik@stanford.edu, pasefrance@dei.unipd.it
Pseudocode Yes We give the pseudocode for Fed PM in Appendix A. Algorithm 1 Fed PM. Algorithm 2 Bayes Agg.
Open Source Code Yes The codebase for this work is open-sourced at https://github.com/BerivanIsik/sparse-random-networks.
Open Datasets Yes We consider four datasets: CIFAR-10 with 10 classes, CIFAR-100 (Krizhevsky et al., 2009) with 100 classes, MNIST (Deng, 2012) with 10 classes, and EMNIST (Cohen et al., 2017) with 47 classes. We only used publicly available standard datasets and included links to them in the manuscript.
Dataset Splits Yes We demonstrate the efficacy of our strategy on MNIST, EMNSIT, CIFAR-10, and CIFAR-100 datasets under both IID and non-IID data splits; and show improvements in accuracy, bitrate, convergence speed, and final model size over relevant baselines, under various system configurations. Clients perform 3 local epochs in all experiments. We provide additional details on the experimental setup in Appendix D. Clients performed 3 local epochs with a batch size of 128 and a local learning rate of 0.1 in all the experiments.
Hardware Specification Yes We conducted our experiments on NVIDIA Titan X GPUs on an internal cluster server, using 1 GPU per one run.
Software Dependencies No While the paper states that its codebase is open-sourced ('The codebase for this work is open-sourced at https://github.com/BerivanIsik/sparse-random-networks.'), it does not explicitly list any specific software dependencies (e.g., Python 3.x, PyTorch 1.x) with their version numbers.
Experiment Setup Yes Clients perform 3 local epochs in all experiments. We provide additional details on the experimental setup in Appendix D. Clients performed 3 local epochs with a batch size of 128 and a local learning rate of 0.1 in all the experiments.