Learning Fair Rule Lists

By Ulrich Matchi Aïvodji, Julien Ferry, Sébastien Gambs, Marie-José Huguet, Mohamed Siala. 2019

11 citations recorded by the source corpus.

As the use of black-box models becomes ubiquitous in high stake decision-making systems, demands for fair and interpretable models are increasing. While it has been shown that interpretable models can be as accurate as black-box models in several critical domains, existing fair classification techniques that are interpretable by design often display poor accuracy/fairness tradeoffs in comparison with their non-interpretable counterparts. In this paper, we propose FairCORELS, a fair classification technique interpretable by design, whose objective is to learn fair rule lists. Our solution is a multi-objective variant of CORELS, a branch-and-bound algorithm to learn rule lists, that supports several statistical notions of fairness. Examples of such measures include statistical parity, equal opportunity and equalized odds. The empirical evaluation of FairCORELS on real-world datasets demonstrates that it outperforms state-of-the-art fair classification techniques that are interpretable by design while being competitive with non-interpretable ones.

Subfields: Artificial Intelligence, Safety Research, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tong Wang
2. Lesia Semenova
3. Chudi Zhong
4. Zhi Chen
5. Haiyang Huang
6. Satoshi Hara
7. Cynthia Rudin
8. Danqing Pan

In Safety Research

1. Tong Wang
2. Lesia Semenova
3. Satoshi Hara
4. Danqing Pan
5. Cynthia Rudin

In AI Ethics, Fairness & Society

1. Lesia Semenova
2. Tong Wang
3. Chudi Zhong
4. Zhi Chen
5. Haiyang Huang
6. Satoshi Hara
7. Danqing Pan
8. Cynthia Rudin

Citations in the corpus

• Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “…can jointly optimize performance metrics and sparsity for decision lists (Rudin and Ertekin, 2016; Yu et al., 2020a; Angelino et al., 2017, 2018; Aı̈vodji et al., 2019) and decision sets (Wang and Rudin, 2015b; Lakkaraju et al., 2016; Ignatiev et al., 2018; Dash et al., 2018b; Malioutov and…”
• Interpretable Companions for Black-Box Models (2020, background): “Many state-of-the-art interpretable models are rule sets [1, 13, 14, 15] or rule lists [8, 9, 16] constructed via various learning algorithms like simulated annealing [17].”