FairCORELS, an Open-Source Library for Learning Fair Rule Lists - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

FairCORELS, an Open-Source Library for Learning Fair Rule Lists

Abstract

FairCORELS is an open-source Python module for building fair rule lists. It is a multi-objective variant of CORELS, a branch-and-bound algorithm to learn certifiably optimal rule lists. FairCORELS supports six statistical fairness metrics, proposes several exploration parameters and leverages on the fairness constraints to prune the search space efficiently. It can easily generate sets of accuracyfairness trade-offs. The models learnt are interpretable by design and a sparsity parameter can be used to control their length. CCS CONCEPTS • Software and its engineering → Software libraries and repositories; • Computing methodologies → Rule learning; Supervised learning; Machine learning algorithms.
Fichier principal
Vignette du fichier
2021_CIKM_DemoTrack_FairCORELS.pdf (490.61 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03427276 , version 1 (13-11-2021)

Identifiers

Cite

Ulrich Aïvodji, Julien Ferry, Sébastien Gambs, Marie-José Huguet, Mohamed Siala. FairCORELS, an Open-Source Library for Learning Fair Rule Lists. ACM International Conference on Information and Knowledge Management, Virtual Event, Nov 2021, Queensland, Australia. pp.4665-4669, ⟨10.1145/3459637.3481965⟩. ⟨hal-03427276⟩
100 View
31 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More