Fair k-Center Clustering for Data Summarization

Authors: Matthäus Kleindessner, Pranjal Awasthi, Jamie Morgenstern

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we present a number of experiments.
Researcher Affiliation Academia 1Department of Computer Science, Rutgers University, NJ 2College of Computing, Georgia Tech, GA.
Pseudocode Yes Algorithm 1 Approximation algorithm for (3), Algorithm 2 Approximation algorithm for (2) when m = 2, Algorithm 3 Algorithm for exchanging centers & finding G, Algorithm 4 Approximation alg. for (2) for arbitrary m
Open Source Code Yes Python code is available on https://github.com/matthklein/fair-k-center-clustering.
Open Datasets Yes Adult data set (Dua & Graff, 2019).
Dataset Splits No The paper describes splitting datasets into demographic groups (e.g., by gender or race) for fairness considerations, but it does not provide explicit details on train/validation/test splits, percentages, or sample counts necessary for reproduction.
Hardware Specification Yes performed on an i Mac with 3.4 GHz i5 / 8 GB DDR4.
Software Dependencies No We implemented the algorithm by Chen et al. (2016) using the generic algorithm for matroid intersection provided in Sage Math. The paper mentions 'Sage Math' but does not specify a version number.
Experiment Setup Yes We only use its six numerical features (e.g., age, hours worked per week), normalized to zero mean and unit variance, for representing records and use the l1distance as metric d.