Group-Fairness in Influence Maximization
Authors: Alan Tsang, Bryan Wilder, Eric Rice, Milind Tambe, Yair Zick
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on real data from an HIV prevention intervention for homeless youth show that standard influence maximization techniques oftentimes neglect smaller groups which contribute less to overall utility, resulting in a disparity which our proposed algorithms substantially reduce. |
| Researcher Affiliation | Academia | 1Department of Computer Science, National University of Singapore 2School of Engineering and Applied Sciences, Harvard University 3Center for AI in Society, University of Southern California |
| Pseudocode | Yes | Algorithm 1 Multiobjective Optimization(γ, τ, T, T , η) ... Algorithm 2 Multiobjective Frank-Wolfe(k, {Wi}) |
| Open Source Code | Yes | all code is available at https://github.com/bwilder0/fair influmax code release. |
| Open Datasets | No | The information is insufficient. The paper states, 'The networks can be made available upon request' for the real-world data, which does not constitute public availability. For the synthetic networks, it only cites 'Wilder et al. [2018c]' without specifying that the dataset itself is publicly accessible through that reference or providing a direct link/DOI to the dataset. |
| Dataset Splits | No | The information is insufficient. The paper does not specify details about training, validation, or testing splits of the datasets, nor does it mention cross-validation or other data partitioning strategies. |
| Hardware Specification | No | The information is insufficient. The paper does not provide any specific hardware details such as GPU/CPU models, memory, or processing units used for running the experiments. |
| Software Dependencies | No | The information is insufficient. The paper does not provide specific software dependencies or their version numbers, such as programming languages, libraries, or solvers. |
| Experiment Setup | Yes | We set the propagation probability to be p = 0.1 and fixed k = 15 seeds (varying these parameters had little impact). |