Model-sharing Games: Analyzing Federated Learning Under Voluntary Participation

Authors: Kate Donahue, Jon Kleinberg5303-5311

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

Reproducibility Variable Result LLM Response
Research Type Theoretical The results in this paper are theoretical and do not depend on any experiments or code.
Researcher Affiliation Academia 1 Department of Computer Science, Cornell University 2 Department of Information Science, Cornell University
Pseudocode No The paper describes algorithms (e.g., 'produce a simple, efficient algorithm to calculate a strictly core-stable arrangement') but does not provide any structured pseudocode or algorithm blocks.
Open Source Code Yes Some of that code is publicly available at github.com/kpdonahue/model_sharing_games.
Open Datasets No The paper is theoretical and does not involve experiments or datasets for training models. Therefore, it does not specify any publicly available datasets used for training.
Dataset Splits No The paper is theoretical and does not involve experiments or datasets. Therefore, it does not provide training/validation/test dataset splits.
Hardware Specification No The paper is theoretical and states that its results do not depend on any experiments. Therefore, it does not specify any hardware used for running experiments.
Software Dependencies No The paper mentions that some code is available on GitHub but does not list any specific software dependencies with version numbers needed for reproducibility.
Experiment Setup No The paper is theoretical and does not involve experiments. Therefore, it does not provide details about an experimental setup, hyperparameters, or training configurations.