research-article

Fairness-Aware Training of Decision Trees by Abstract Interpretation

Authors:

Francesco Ranzato,

Caterina Urban,

Marco ZanellaAuthors Info & Claims

CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management

Pages 1508 - 1517

https://doi.org/10.1145/3459637.3482342

Published: 30 October 2021 Publication History

Abstract

We study the problem of formally verifying individual fairness of decision tree ensembles, as well as training tree models which maximize both accuracy and individual fairness. In our approach, fairness verification and fairness-aware training both rely on a notion of stability of a classifier, which is a generalization of the standard notion of robustness to input perturbations used in adversarial machine learning. Our verification and training methods leverage abstract interpretation, a well-established mathematical framework for designing computable, correct, and precise approximations of potentially infinite behaviors. We implemented our fairness-aware learning method by building on a tool for adversarial training of decision trees. We evaluated it in practice on the reference datasets in the literature on fairness in machine learning. The experimental results show that our approach is able to train tree models exhibiting a high degree of individual fairness with respect to the natural state-of-the-art CART trees and random forests. Moreover, as a by-product, these fairness-aware decision trees turn out to be significantly compact, which naturally enhances their interpretability.

References

[1]

Sina Aghaei, Mohammad Javad Azizi, and Phebe Vayanos. 2019. Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019. AAAI Press, 1418--1426. https://doi.org/10.1609/aaai.v33i01.33011418

[2]

Maksym Andriushchenko and Matthias Hein. 2019. Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks. In Proc. 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019). https://proceedings.neurips.cc/paper/2019/hash/4206e38996fae4028a26d43b24f68d32-Abstract.html

Digital Library

[3]

Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine Bias. ProPublica, May, Vol. 23 (2016), 2016. https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing

[4]

Solon Barocas and Andrew D. Selbst. 2016. Big Data's Disparate Impact. California Law Review, Vol. 104 (2016), 671. https://doi.org/10.15779/Z38BG31

[5]

Dimitris Bertsimas and Jack Dunn. 2017. Optimal classification trees. Mach. Learn., Vol. 106, 7 (2017), 1039--1082. https://doi.org/10.1007/s10994-017-5633-9

Digital Library

[6]

Max Bramer. 2013. Avoiding Overfitting of Decision Trees. Springer, 121--136. https://doi.org/10.1007/978-1-4471-4884--5_9

[7]

Leo Breiman. 2001. Random Forests. Machine Learning, Vol. 45, 1 (2001), 5--32. https://doi.org/10.1023/A:1010933404324

Digital Library

[8]

Leo Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone. 1984. Classification and Regression Trees. Wadsworth.

[9]

Joy Buolamwini and Timnit Gebru. 2018. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification. In Conference on Fairness, Accountability and Transparency (FAT 2018) (Proceedings of Machine Learning Research, Vol. 81). PMLR, 77--91. http://proceedings.mlr.press/v81/buolamwini18a.html

[10]

Stefano Calzavara, Claudio Lucchese, and Gabriele Tolomei. 2019. Adversarial Training of Gradient-Boosted Decision Trees. In Proc. 28th ACM International Conference on Information and Knowledge Management (CIKM 2019). 2429--2432. https://doi.org/10.1145/3357384.3358149

Digital Library

[11]

Stefano Calzavara, Claudio Lucchese, Gabriele Tolomei, Seyum Assefa Abebe, and Salvatore Orlando. 2020. TREANT: training evasion-aware decision trees. Data Mining and Knowledge Discovery (2020). https://doi.org/10.1007/s10618-020-00694--9

[12]

Nicholas Carlini and David A. Wagner. 2017. Towards Evaluating the Robustness of Neural Networks. In Proc. of 38th IEEE Symposium on Security and Privacy (S & P 2017). 39--57. https://doi.org/10.1109/SP.2017.49

[13]

Hongge Chen, Huan Zhang, Duane S. Boning, and Cho-Jui Hsieh. 2019. Robust Decision Trees Against Adversarial Examples. In Proc. 36th Int. Conf. on Machine Learning, (ICML 2019). 1122--1131. http://proceedings.mlr.press/v97/chen19m.html

[14]

Alexandra Chouldechova. 2017. Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments. Big Data, Vol. 5, 2 (2017), 153--163. https://doi.org/10.1089/big.2016.0047

[15]

Patrick Cousot. 2021. Principles of Abstract Interpretation. MIT Press.

[16]

Patrick Cousot and Radhia Cousot. 1977. Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints. In Proc. 4th ACM Symposium on Principles of Programming Languages (POPL 1977). 238--252. https://doi.org/10.1145/512950.512973

Digital Library

[17]

Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository.

[18]

Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard S. Zemel. 2012. Fairness through awareness. In Innovations in Theoretical Computer Science 2012. ACM, 214--226. https://doi.org/10.1145/2090236.2090255

Digital Library

[19]

European Commission. 2021. Proposal for a Regulation Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act). https://digital-strategy.ec.europa.eu/en/library/proposal-regulation-laying-down-harmonised-rules-artificial-intelligence-artificial-intelligence.

[20]

Jerome H Friedman. 2001. Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics (2001), 1189--1232. https://www.jstor.org/stable/2699986

[21]

Sainyam Galhotra, Yuriy Brun, and Alexandra Meliou. 2017. Fairness Testing: Testing Software for Discrimination. In FSE. 498--510. https://doi.org/10.1145/3106237.3106277

Digital Library

[22]

Ian Goodfellow, Patrick McDaniel, and Nicolas Papernot. 2018. Making Machine Learning Robust Against Adversarial Inputs. Commun. ACM, Vol. 61, 7 (2018), 56--66. https://doi.org/10.1145/3134599

Digital Library

[23]

Vincent Grari, Boris Ruf, Sylvain Lamprier, and Marcin Detyniecki. 2020. Achieving Fairness with Decision Trees: An Adversarial Approach. Data Sci. Eng., Vol. 5, 2 (2020), 99--110. https://doi.org/10.1007/s41019-020-00124-2

[24]

Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of Opportunity in Supervised Learning. In Proc. 30th Annual Conference on Neural Information Processing Systems (NeurIPS 2016). 3315--3323. http://papers.nips.cc/paper/6374-equality-of-opportunity-in-supervised-learning

Digital Library

[25]

John H Holland. 1984. Genetic algorithms and adaptation. In Adaptive Control of Ill-Defined Systems. Springer, 317--333. https://doi.org/10.1007/978-1-4684-8941-5_21

[26]

Alex Kantchelian, J. D. Tygar, and Anthony D. Joseph. 2016. Evasion and Hardening of Tree Ensemble Classifiers. In Proc. 33rd International Conference on Machine Learning (ICML 2016). 2387--2396. http://dl.acm.org/citation.cfm?id=3045390.3045642

Digital Library

[27]

Matthew Kay, Cynthia Matuszek, and Sean A. Munson. 2015. Unequal Representation and Gender Stereotypes in Image Search Results for Occupations. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems (CHI 2015). ACM, 3819--3828. https://doi.org/10.1145/2702123.2702520

Digital Library

[28]

Michael J. Kearns and Yishay Mansour. 1998. A Fast, Bottom-Up Decision Tree Pruning Algorithm with Near-Optimal Generalization. In Proceedings of the Fifteenth International Conference on Machine Learning (ICML 1998). Morgan Kaufmann, 269--277. https://dl.acm.org/doi/10.5555/645527.657457

Digital Library

[29]

Amir E. Khandani, Adlar J. Kim, and Andrew W. Lo. 2010. Consumer Credit-Risk Models via Machine-Learning Algorithms. Journal of Banking & Finance, Vol. 34, 11 (2010), 2767--2787. https://doi.org/10.1016/j.jbankfin.2010.06.001

[30]

Changliu Liu, Tomer Arnon, Christopher Lazarus, Christopher A. Strong, Clark W. Barrett, and Mykel J. Kochenderfer. 2021. Algorithms for Verifying Deep Neural Networks. Found. Trends Optim., Vol. 4, 3-4 (2021), 244--404. https://doi.org/10.1561/2400000035

Digital Library

[31]

Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2021. A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv., Vol. 54, 6, Article 115 (July 2021), bibinfonumpages35 pages. https://doi.org/10.1145/3457607

Digital Library

[32]

Frank Neumann, Pietro Simone Oliveto, and Carsten Witt. 2009. Theoretical Analysis of Fitness-Proportional Selection: Landscapes and Efficiency. In Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation (GECCO 2009) (Montreal, Québec, Canada). ACM, 835--842. https://doi.org/10.1145/1569901.1570016

Digital Library

[33]

Ziad Obermeyer, Brian Powers, Christine Vogeli, and Sendhil Mullainathan. 2019. Dissecting Racial Bias in an Algorithm Used to Manage the Health of Populations. Science Vol. 366 (2019), 447--453. Issue 6464. https://doi.org/10.1126/science.aax2342

[34]

Edward Raff, Jared Sylvester, and Steven Mills. 2018. Fair Forests: Regularized Tree Induction to Minimize Model Bias. In Proc. 1st AAAI/ACM Conference on AI, Ethics, and Society (AIES 2018). 243--250. https://doi.org/10.1145/3278721.3278742

Digital Library

[35]

Francesco Ranzato, Caterina Urban, and Marco Zanella. 2021. FATT: Fairness Aware Tree Training. https://github.com/fatt21/fatt.

[36]

Francesco Ranzato and Marco Zanella. 2020. Abstract Interpretation of Decision Tree Ensemble Classifiers. In Proc. 34th AAAI Conference on Artificial Intelligence (AAAI 2020). 5478--5486. https://aaai.org/ojs/index.php/AAAI/article/view/5998

[37]

Francesco Ranzato and Marco Zanella. 2021. Genetic Adversarial Training of Decision Trees. In Proceedings of the Genetic and Evolutionary Computation Conference (Lille, France) (GECCO '21). Association for Computing Machinery, New York, NY, USA, 358--367. https://doi.org/10.1145/3449639.3459286

Digital Library

[38]

Xavier Rival and Kwangkeun Yi. 2020. Introduction to Static Analysis: An Abstract Interpretation Perspective. The MIT Press.

[39]

Yuji Roh, Kangwook Lee, Steven Whang, and Changho Suh. 2020. FR-Train: A Mutual Information-Based Approach to Fair and Robust Training. In Proc. of the 37th Int. Conf. on Machine Learning (ICML 2020) (Proceedings of Machine Learning Research, Vol. 119). PMLR, 8147--8157. http://proceedings.mlr.press/v119/roh20a.html

[40]

Anian Ruoss, Mislav Balunovic, Marc Fischer, and Martin T. Vechev. 2020. Learning Certified Individually Fair Representations. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS 2020). https://proceedings.neurips.cc/paper/2020/hash/55d491cf951b1b920900684d71419282-Abstract.html

[41]

Candice Schumann, Jeffrey S. Foster, Nicholas Mattei, and John P. Dickerson. 2020. We Need Fairness and Explainability in Algorithmic Hiring. In Proc. 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020). 1716--1720. https://dl.acm.org/doi/abs/10.5555/3398761.3398960

Digital Library

[42]

M. Srinivas and L. M. Patnaik. 1994. Genetic algorithms: a survey. Computer, Vol. 27, 6 (1994), 17--26. https://doi.org/10.1109/2.294849

Digital Library

[43]

Caterina Urban, Maria Christakis, Valentin Wü stholz, and Fuyuan Zhang. 2020. Perfectly parallel fairness certification of neural networks. Proc. ACM Program. Lang., Vol. 4, OOPSLA (2020), 185:1--185:30. https://doi.org/10.1145/3428253

Digital Library

[44]

Caterina Urban and Antoine Miné. 2021. A Review of Formal Methods applied to Machine Learning. CoRR, Vol. abs/2104.02466 (2021). https://arxiv.org/abs/2104.02466

[45]

Mikhail Yurochkin, Amanda Bower, and Yuekai Sun. 2020. Training individually fair ML models with sensitive subspace robustness. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https://openreview.net/forum?id=B1gdkxHFDH

[46]

Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez-Rodriguez, and Krishna P. Gummadi. 2017. Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment. In Proc. 26th International Conference on World Wide Web (WWW 2017). 1171--1180. https://doi.org/10.1145/3038912.3052660

Digital Library

Cited By

Hort MChen ZZhang JHarman MSarro F(2024)Bias Mitigation for Machine Learning Classifiers: A Comprehensive SurveyACM Journal on Responsible Computing10.1145/36313261:2(1-52)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3631326
Zhu HYi CRho SLiu SJiang F(2024)An Interpretable Multivariate Time-Series Anomaly Detection Method in Cyber–Physical Systems Based on Adaptive MaskIEEE Internet of Things Journal10.1109/JIOT.2023.329386011:2(2728-2740)Online publication date: 15-Jan-2024
https://doi.org/10.1109/JIOT.2023.3293860
Fassina NRanzato FZanella M(2024)Robustness verification of k-nearest neighbors by abstract interpretationKnowledge and Information Systems10.1007/s10115-024-02108-466:8(4825-4859)Online publication date: 1-Aug-2024
https://dl.acm.org/doi/10.1007/s10115-024-02108-4
Show More Cited By

Index Terms

Fairness-Aware Training of Decision Trees by Abstract Interpretation

Recommendations

Improve individual fairness in federated learning via adversarial training
Highlights
- We present an adversarial training approach for training FL models that satisfy individual fairness without requiring direct access to training data or the underlying data distribution, thereby protecting user privacy at the same time.
Abstract
Federated learning (FL) has been widely investigated these years. Since FL will be universally applied in the real world, the fairness issue involved is worthy of attention, while there are few relevant studies. Unlike previous work on group ...
Incremental Induction of Decision Trees

This article presents an incremental algorithm for inducing decision trees equivalent to those formed by Quinlan's nonincremental ID3 algorithm, given the same training instances. The new algorithm, named ID5R, lets one apply the ID3 induction process ...
Word Sense Disambiguation by Learning Decision Trees from Unlabeled Data

In this paper we describe a machine learning approach to word sense disambiguation that uses unlabeled data. Our method is based on selective sampling with committees of decision trees. The committee members are trained on a small set of labeled ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management

October 2021

4966 pages

ISBN:9781450384469

DOI:10.1145/3459637

General Chairs:
Gianluca Demartini
The University of Queensland, Australia
,
Guido Zuccon
The University of Queensland, Australia
,
Program Chairs:
J. Shane Culpepper
RMIT University, Australia
,
Zi Huang
The University of Queensland, Australia
,
Hanghang Tong
University of Illinois at Urbana-Champaign, USA

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 30 October 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Facebook Research award
University of Padova
Italian Ministry of University and Research

Conference

CIKM '21

Sponsor:

CIKM '21: The 30th ACM International Conference on Information and Knowledge Management

November 1 - 5, 2021

Queensland, Virtual Event, Australia

Acceptance Rates

Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
262
Total Downloads

Downloads (Last 12 months)68
Downloads (Last 6 weeks)3

Reflects downloads up to 23 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Hort MChen ZZhang JHarman MSarro F(2024)Bias Mitigation for Machine Learning Classifiers: A Comprehensive SurveyACM Journal on Responsible Computing10.1145/36313261:2(1-52)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3631326
Zhu HYi CRho SLiu SJiang F(2024)An Interpretable Multivariate Time-Series Anomaly Detection Method in Cyber–Physical Systems Based on Adaptive MaskIEEE Internet of Things Journal10.1109/JIOT.2023.329386011:2(2728-2740)Online publication date: 15-Jan-2024
https://doi.org/10.1109/JIOT.2023.3293860
Fassina NRanzato FZanella M(2024)Robustness verification of k-nearest neighbors by abstract interpretationKnowledge and Information Systems10.1007/s10115-024-02108-466:8(4825-4859)Online publication date: 1-Aug-2024
https://dl.acm.org/doi/10.1007/s10115-024-02108-4
Pal ARanzato FUrban CZanella M(2024)Abstract Interpretation-Based Feature Importance for Support Vector MachinesVerification, Model Checking, and Abstract Interpretation10.1007/978-3-031-50524-9_2(27-49)Online publication date: 15-Jan-2024
https://dl.acm.org/doi/10.1007/978-3-031-50524-9_2
Calzavara SCazzaro LLucchese CMarcuzzi F(2023)Explainable Global Fairness Verification of Tree-Based Classifiers2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)10.1109/SaTML54575.2023.00011(1-17)Online publication date: Feb-2023
https://doi.org/10.1109/SaTML54575.2023.00011
Fassina NRanzato FZanella M(2023)Robustness Certification of k-Nearest Neighbors2023 IEEE International Conference on Data Mining (ICDM)10.1109/ICDM58522.2023.00020(110-119)Online publication date: 1-Dec-2023
https://doi.org/10.1109/ICDM58522.2023.00020

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents