Learning Strategic Network Emergence Games

Authors: Rakshit Trivedi, Hongyuan Zha

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In the experiments, we demonstrate that MINE learns versatile payoff mechanisms that: highly correlates with the ground truth for a synthetic case; can be used to analyze the observed network structure; and enable effective transfer in specific settings.
Researcher Affiliation Academia Rakshit Trivedi Georgia Institute of Technology rstrivedi@gatech.edu Hongyuan Zha AIRS and Chinese University of Hong Kong, Shenzhen zha@cc.gatech.edu
Pseudocode Yes Algorithm 1 in Appendix B outlines complete training procedure.
Open Source Code No The paper does not provide an explicit statement or link for open-source code availability for the methodology described.
Open Datasets Yes We consider Australian bank dataset [37] (Figure 2(a)), a small network of strategic confiding relationships between branch personnel representing hierarchy among the employees.
Dataset Splits No The paper mentions splitting data into train and test sets, but does not explicitly describe a separate validation set or its usage for hyperparameter tuning or model selection.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not list specific version numbers for software dependencies or libraries used in the implementation.
Experiment Setup No We provide more details on experimental setup in Appendix C and dataset statistics in Table 2(c).