Individual Fairness in Kidney Exchange Programs

Authors: Golnoosh Farnadi, William St-Arnaud, Behrouz Babaki, Margarida Carvalho11496-11505

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our methodology enables decision makers to fully control KEP outcomes, overcoming any potential bias or vulnerability intrinsic to a deterministic solver. The advantages of our proposed method over the common practice of using the optimal solution obtained by a solver are stressed through computational experiments. In this section, we show the effectiveness of our proposed methods by performing an empirical evaluation.
Researcher Affiliation Academia 1 CIRRELT and Universit e de Montr eal, 2 HEC Montr eal, 3 Mila, 4 Polytechnique Montr eal
Pseudocode Yes Algorithm 1: Class Kep Constraint
Open Source Code Yes The code and data is available online2. 2https://github.com/stawaway/IF-KEP
Open Datasets Yes For all the empirical evaluations that are presented in this section, we use two datasets which we name the US dataset (Saidman et al. 2006) and the Canada dataset (Carvalho and Lodi 2019).
Dataset Splits No The paper evaluates its methods on two datasets (US and Canada datasets) with varying graph sizes (20, 30, ..., 70 vertices), but it does not specify explicit training, validation, or test dataset splits in terms of percentages or sample counts for these experimental evaluations.
Hardware Specification No The paper states that research was supported by Calcul Qu ebec and Compute Canada, which are high-performance computing consortia, but it does not provide specific hardware details such as GPU models, CPU types, or memory specifications used for the experiments.
Software Dependencies No The paper refers to using Integer Linear Programming (ILP) and Constraint Programming (CP) methodologies, and mentions solvers generally, but does not provide specific version numbers for any software dependencies, libraries, or solvers used in their experimental setup.
Experiment Setup Yes However, for half of the instances of larger graphs, enumerating all optimal solutions within the timeout (30 minutes) is still not possible.