Incentives in Federated Learning: Equilibria, Dynamics, and Mechanisms for Welfare Maximization

Authors: Aniket Murhekar, Zhuowen Yuan, Bhaskar Ray Chaudhury, Bo Li, Ruta Mehta

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our empirical validation on MNIST and CIFAR-10 substantiates our theoretical analysis.
Researcher Affiliation Academia Aniket Murhekar1 Zhuowen Yuan1 Bhaskar Ray Chaudhury1 Bo Li1 Ruta Mehta1 1University of Illinois, Urbana-Champaign
Pseudocode Yes We present the full description of the algorithm for Fed BR-BG and Fed BR as Algorithm 1 and Algorithm 2 in Appendix C, respectively.
Open Source Code No The paper does not contain an explicit statement about the release of its source code or a link to a code repository.
Open Datasets Yes We perform the evaluation on the MNIST (Le Cun et al. [2010]) and CIFAR-10 (Krizhevsky [2009]) datasets.
Dataset Splits No The paper states 'each agent has 100 training images and 10 testing images' but does not specify a validation split or how validation was handled.
Hardware Specification No The paper does not specify the hardware used for running the experiments. It mentions model architectures (CNN, VGG11) but not the underlying computational resources.
Software Dependencies No The paper does not list specific software dependencies with version numbers.
Experiment Setup Yes We set global learning rate η to 1.0, local learning rate α to 0.01, and momentum to 0.9. We set the number of contribution updating steps to 100 and the sample number interval to 10.