2023

Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and finance

Chen, Dangxing, Zhang, Luyao

Understand

Algorithm fairness in the application of artificial intelligence (AI) is essential for a better society.

As the foundational axiom of social mechanisms, fairness consists of multiple facets.
Although the machine learning (ML) community has focused on intersectionality as a matter of statistical parity, especially in discrimination issues, an emerging body of literature addresses another facet -- monotonicity.
Based on domain expertise, monotonicity plays a vital role in numerous fairness-related areas, where violations could misguide human decisions and lead to disastrous consequences.

Built on

An intersectional definition of fairness. In 2020 IEEE 36th International Conference on Data Engineering (ICDE) . IEEE, 1918–1921
James R Foulds, Rashidul Islam, Kamrun Naher Keya, and Shimei Pan. 2020 · 1921
Earlier work this paper cites.
Approximation by superpositions of a sigmoidal function
George Cybenko. 1989 · 1989
Earlier work this paper cites.
Approximation capabilities of multilayer feedforward networks
Kurt Hornik. 1991 · 1991
Earlier work this paper cites.
Fundamentals of artificial neural networks
Mohamad H Hassoun et al · 1995
Earlier work this paper cites.
LSAC National Longitudinal Bar Passage Study. LSAC Research Report Series
Linda F Wightman. 1998 · 1998
Earlier work this paper cites.
Neural networks: a comprehensive foundation by Simon Haykin, Macmillan, 1994, ISBN 0-02-352781-7
Miroslav Kubat. 1999 · 1999
Earlier work this paper cites.
Diminishing marginal utility of income? Caveat emptor
Richard A Easterlin. 2005 · 2005
Earlier work this paper cites.
Diminishing marginal returns and the production of education: An international analysis
Douglas N Harris. 2007 · 2007
Earlier work this paper cites.
Learning fair representations. In International conference on machine learning . PMLR, 325–333
Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork. 2013 · 2013
Earlier work this paper cites.
Boosted SVM for extracting rules from imbalanced data in application to prediction of the post-operative life expectancy in the lung cancer patients
Maciej Zięba, Jakub M Tomczak, Marek Lubicz, and Jerzy Świątek. 2014 · 2014
Earlier work this paper cites.
Certifying and removing disparate impact. In proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining . 259–268
Michael Feldman, Sorelle A Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian. 2015 · 2015
Earlier work this paper cites.
Machine bias: There’s software used across the country to predict future criminals. And it’s biased against blacks
2016 · 2016
Earlier work this paper cites.
ProPublica. COMPAS data and analysis for “Machine bias"
2016 · 2016
Earlier work this paper cites.
Equality of opportunity in supervised learning
Moritz Hardt, Eric Price, and Nati Srebro. 2016 · 2016
Earlier work this paper cites.
Fast and flexible monotonic functions with ensembles of lattices
Mahdi Milani Fard, Kevin Canini, Andrew Cotter, Jan Pfeifer, and Maya Gupta. 2016 · 2016
Earlier work this paper cites.
Generalized additive models
Trevor J Hastie. 2017 · 2017
Earlier work this paper cites.

Similar

Deep lattice networks and partial monotonic functions
Seungil You, David Ding, Kevin Canini, Jan Pfeifer, and Maya Gupta. 2017 · 2017
Cited alongside, same era.
An interpretable model with globally consistent explanations for credit risk
Original
Chaofan Chen, Kangcheng Lin, Cynthia Rudin, Yaron Shaposhnik, Sijia Wang, and Tong Wang. 2018 · 2018
Cited alongside, same era.
The accuracy, fairness, and limits of predicting recidivism
Julia Dressel and Hany Farid. 2018 · 2018
Cited alongside, same era.
Human decisions and machine predictions
Jon Kleinberg, Himabindu Lakkaraju, Jure Leskovec, Jens Ludwig, and Sendhil Mullainathan. 2018 · 2018
Cited alongside, same era.
How artificial intelligence and machine learning can impact market design
Paul R Milgrom and Steven Tadelis. 2018 · 2018
Cited alongside, same era.
Distill-and-compare: Auditing black-box models using transparent model distillation. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society . 303–310
Sarah Tan, Rich Caruana, Giles Hooker, and Yin Lou. 2018 · 2018
Cited alongside, same era.
Guidelines for human-AI interaction. In Proceedings of the 2019 chi conference on human factors in computing systems . 1–13
Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N Bennett, Kori Inkpen, et al · 2019
Cited alongside, same era.
Machine learning methods that economists should know about
Susan Athey and Guido W Imbens. 2019 · 2019
Cited alongside, same era.
Fairness-aware machine learning: Practical challenges and lessons learned. In Proceedings of the twelfth ACM international conference on web search and data mining . 834–835
Sarah Bird, Krishnaram Kenthapadi, Emre Kiciman, and Margaret Mitchell. 2019 · 2019
Cited alongside, same era.
Explainable AI in industry. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining . 3203–3204
Krishna Gade, Sahin Cem Geyik, Krishnaram Kenthapadi, Varun Mithal, and Ankur Taly. 2019 · 2019
Cited alongside, same era.
XAI—Explainable artificial intelligence
David Gunning, Mark Stefik, Jaesik Choi, Timothy Miller, Simone Stumpf, and Guang-Zhong Yang. 2019 · 2019
Cited alongside, same era.
Explainable AI: A brief survey on history, research areas, approaches and challenges. In CCF international conference on natural language processing and Chinese computing . Springer, 563–574
Feiyu Xu, Hans Uszkoreit, Yangzhou Du, Wei Fan, Dongyan Zhao, and Jun Zhu. 2019 · 2019
Cited alongside, same era.

Then

Enhancing explainability of neural networks through architecture constraints
Zebin Yang, Aijun Zhang, and Agus Sudjianto. 2020 · 2020
Later among the works it cites.
European Union’s Artificial Intelligence Act
2021 · 2021
Later among the works it cites.
Neural additive models: Interpretable machine learning with neural nets
Rishabh Agarwal, Levi Melnick, Nicholas Frosst, Xuezhou Zhang, Ben Lengerich, Rich Caruana, and Geoffrey E Hinton. 2021 · 2021
Later among the works it cites.
AI regulation is coming
Charme di Carlo, Midas De Bondt, and Theodoros Evgeniou. 2021 · 2021
Later among the works it cites.
The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systems
Original
Dominik Dellermann, Adrian Calma, Nikolaus Lipusch, Thorsten Weber, Sascha Weigel, and Philipp Ebel. 2021 · 2021
Later among the works it cites.
Ethics of Artificial Intelligence and Robotics
Vincent C. Müller. 2021 · 2021
Later among the works it cites.
Toward causal representation learning
Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, and Yoshua Bengio. 2021 · 2021
Later among the works it cites.
Formal Approaches to Social Procedures
Jan van Eijck and Rineke (L.C.) Verbrugge. 2021 · 2021
Later among the works it cites.
GAMI-Net: An explainable neural network based on generalized additive models with structured interactions
Zebin Yang, Aijun Zhang, and Agus Sudjianto. 2021 · 2021
Later among the works it cites.
Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for Credit Scoring. In Proceedings of the Third ACM International Conference on AI in Finance . 70–78
Dangxing Chen and Weicheng Ye. 2022 · 2022
Later among the works it cites.
Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects
Elena Dumitrescu, Sullivan Hue, Christophe Hurlin, and Sessi Tokpavi. 2022 · 2022
Later among the works it cites.
How is machine learning useful for macroeconomic forecasting?
Philippe Goulet Coulombe, Maxime Leroux, Dalibor Stevanovic, and Stéphane Surprenant. 2022 · 2022
Later among the works it cites.
Socially situated artificial intelligence enables learning from human interaction
Ranjay Krishna, Donsuk Lee, Li Fei-Fei, and Michael S Bernstein. 2022 · 2022
Later among the works it cites.
A Review on Fairness in Machine Learning
Dana Pessach and Erez Shmueli. 2022 · 2022
Later among the works it cites.
Deontological ethics by monotonicity shape constraints. In International Conference on Artificial Intelligence and Statistics . PMLR, 2043–2054
Serena Wang and Maya Gupta. 2020 · 2054
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…