research-article

Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition

Authors:

Changshui Zhang,

Fei WangAuthors Info & Claims

KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining

Pages 1287 - 1297

https://doi.org/10.1145/3447548.3467258

Published: 14 August 2021 Publication History

Abstract

Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the development of quantitative metrics to measure algorithm disparities across different protected groups, and approaches for adjusting the algorithm output to reduce such disparities. In this paper, we propose to study the problem of identification of the source of model disparities. Unlike existing interpretation methods which typically learn feature importance, we consider the causal relationships among feature variables and propose a novel framework to decompose the disparity into the sum of contributions from fairness-aware causal paths, which are paths linking the sensitive attribute and the final predictions, on the graph. We also consider the scenario when the directions on certain edges within those paths cannot be determined. Our framework is also model agnostic and applicable to a variety of quantitative disparity measures. Empirical evaluations on both synthetic and real-world data sets are provided to show that our method can provide precise and comprehensive explanations to the model disparities.

Supplementary Material

MP4 File (explaining_algorithmic_fairness_through_fairnessaware-weishen_pan-sen_cui-38957832-zpeH.mp4)

Presentation video

Download
104.58 MB

References

[1]

Kjersti Aas, Martin Jullum, and Anders Løland. 2019. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. arXiv preprint arXiv:1903.10464 (2019).

[2]

Ayodeji Adegunsoye, Iazsmin Bauer Ventura, and Vladimir M Liarski. 2020. Association of black race with outcomes in COVID-19 disease: a retrospective cohort study. Annals of the American Thoracic Society, Vol. 17, 10 (2020), 1336--1339.

[3]

Alekh Agarwal, Alina Beygelzimer, Miroslav Dudík, John Langford, and Hanna Wallach. 2018. A reductions approach to fair classification. In International Conference on Machine Learning. PMLR, 60--69.

[4]

Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine bias: There's software used across the country to predict future criminals. And it's biased against blacks. ProPublica, Vol. 23 (2016).

[5]

Benjamin R Baer, Daniel E Gilbert, and Martin T Wells. 2019. Fairness criteria through the lens of directed acyclic graphical models. arXiv preprint arXiv:1906.11333 (2019).

[6]

Tom Begley, Tobias Schwedes, Christopher Frye, and Ilya Feige. 2020. Explainability for fair machine learning. arXiv preprint arXiv:2010.07389 (2020).

[7]

Giorgos Borboudakis and Ioannis Tsamardinos. 2012. Incorporating causal prior knowledge as path-constraints in bayesian networks and maximal ancestral graphs. In Proceedings of the 29th International Coference on International Conference on Machine Learning. 427--434.

Digital Library

[8]

Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 785--794.

Digital Library

[9]

Silvia Chiappa. 2019. Path-specific counterfactual fairness. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 7801--7808.

Digital Library

[10]

Christine S Cox. 1998. Plan and operation of the NHANES I Epidemiologic Followup Study, 1992. Number 35. National Ctr for Health Statistics.

[11]

Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. 2012. Fairness through awareness. In Proceedings of the 3rd innovations in theoretical computer science conference. 214--226.

Digital Library

[12]

Christopher Frye, Colin Rowat, and Ilya Feige. 2020. Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability. Advances in Neural Information Processing Systems, Vol. 33 (2020).

[13]

Elise Gould and Valerie Wilson. 2020. Black workers face two of the most lethal preexisting conditions for coronavirus-Racism and economic inequality. Economic Policy Institute, Vol. 1 (2020).

[14]

Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of Opportunity in Supervised Learning. In Advances in Neural Information Processing Systems. 3315--3323.

[15]

Tom Heskes, Evi Sijben, Ioan Gabriel Bucur, and Tom Claassen. 2020. Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models. Advances in Neural Information Processing Systems, Vol. 33 (2020).

[16]

Aapo Hyärinen and Petteri Pajunen. 1999. Nonlinear independent component analysis: Existence and uniqueness results. Neural networks, Vol. 12, 3 (1999), 429--439.

[17]

Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, and Bernhard Schölkopf. 2017. Avoiding discrimination through causal reasoning. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 656--666.

Digital Library

[18]

Matt J Kusner, Joshua Loftus, Chris Russell, and Ricardo Silva. 2017. Counterfactual fairness. In Advances in neural information processing systems. 4066--4076.

[19]

Moshe Lichman et al. 2013. UCI machine learning repository.

[20]

Scott M Lundberg. 2020. Explaining Quantitative Measures of Fairness. Fair & Responsible AI Workshop @ CHI2020 (2020).

[21]

Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Advances in neural information processing systems. 4765--4774.

[22]

David Madras, Elliot Creager, Toniann Pitassi, and Richard Zemel. 2018. Learning Adversarially Fair and Transferable Representations. In International Conference on Machine Learning. 3384--3393.

[23]

Diego A Martinez, Jeremiah S Hinson, Eili Y Klein, Nathan A Irvin, Mustapha Saheed, Kathleen R Page, and Scott R Levin. 2020. SARS-CoV-2 positivity rate for Latinos in the Baltimore--Washington, DC Region. Jama, Vol. 324, 4 (2020), 392--395.

[24]

Razieh Nabi and Ilya Shpitser. 2018. Fair inference on outcomes. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32.

[25]

Emilija Perkovic. 2020. Identifying causal effects in maximally oriented partially directed acyclic graphs. In Conference on Uncertainty in Artificial Intelligence. PMLR, 530--539.

[26]

Eboni G Price-Haywood, Jeffrey Burton, Daniel Fort, and Leonardo Seoane. 2020. Hospitalization and mortality among black patients and white patients with Covid-19. New England Journal of Medicine (2020).

[27]

Jiaming Song, Pratyusha Kalluri, Aditya Grover, Shengjia Zhao, and Stefano Ermon. 2019. Learning controllable fair representations. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 2164--2173.

[28]

Peter Spirtes, Clark N Glymour, Richard Scheines, and David Heckerman. 2000. Causation, prediction, and search. MIT press.

[29]

Jiaxuan Wang, Jenna Wiens, and Scott Lundberg. 2021. Shapley flow: A graph-based approach to interpreting model predictions. In International Conference on Artificial Intelligence and Statistics. PMLR, 721--729.

[30]

Julia A Wolfson and Cindy W Leung. 2020. Food Insecurity and COVID-19: Disparities in Early Effects for US Adults. Nutrients, Vol. 12, 6 (2020), 1648.

[31]

Yongkai Wu, Lu Zhang, Xintao Wu, and Hanghang Tong. 2019. Pc-fairness: A unified framework for measuring causality-based fairness. In Advances in Neural Information Processing Systems. 3404--3414.

[32]

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 Proceedings of the 26th international conference on world wide web. 1171--1180.

Digital Library

[33]

Brian Hu Zhang, Blake Lemoine, and Margaret Mitchell. 2018a. Mitigating unwanted biases with adversarial learning. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society. 335--340.

Digital Library

[34]

Lu Zhang, Yongkai Wu, and Xintao Wu. 2018b. Causal modeling-based discrimination discovery and removal: Criteria, bounds, and algorithms. IEEE Transactions on Knowledge and Data Engineering, Vol. 31, 11 (2018), 2035--2050.

Digital Library

Cited By

Deck LSchoeffer JDe-Arteaga MKühl N(2024)A Critical Survey on Fairness Benefits of Explainable AIProceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency10.1145/3630106.3658990(1579-1595)Online publication date: 3-Jun-2024
https://dl.acm.org/doi/10.1145/3630106.3658990
Fragkathoulas CPapanikou VKaridi DPitoura E(2024)On Explaining Unfairness: An Overview2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW)10.1109/ICDEW61823.2024.00035(226-236)Online publication date: 13-May-2024
https://doi.org/10.1109/ICDEW61823.2024.00035
Mehari MSibih YDada AChang SWen PMolinaro AChukwueke UBudhu JJackson SMcFaline-Figueroa JPorter AHervey-Jumper S(2024)Enhancing neuro-oncology care through equity-driven applications of artificial intelligenceNeuro-Oncology10.1093/neuonc/noae127Online publication date: 19-Aug-2024
https://doi.org/10.1093/neuonc/noae127
Show More Cited By

Index Terms

Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
2. Mathematics of computing
  1. Probability and statistics
    1. Probabilistic representations
      1. Causal networks

Recommendations

Airtime Fairness for IEEE 802.11 Multirate Networks

Under a multi rate network scenario, the IEEE 802.11 DCF MAC fails to provide air-time fairness for all competing stations since the protocol is designed for ensuring max-min throughput fairness and the maximum achievable throughput by any station gets ...
Counterfactual Explanation for Fairness in Recommendation
Fairness-aware recommendation alleviates discrimination issues to build trustworthy recommendation systems. Explaining the causes of unfair recommendations is critical, as it promotes fairness diagnostics, and thus secures users’ trust in recommendation ...
A practical approach to explaining defect proneness of code commits by causal discovery
Abstract
Explainable software defect prediction is practical for software quality assurance. However, it is hard to explain the predictions made by obscure machine learning models because of the lack of transparency and the unreliability of the ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining

August 2021

4259 pages

ISBN:9781450383325

DOI:10.1145/3447548

General Chairs:
Feida Zhu
Singapore Management University
,
Beng Chin Ooi
National University of Singapore
,
Chunyan Miao
Nanyang Technology University
,
Program Chairs:
Haixun Wang,
Iryna Skrypnyk,
Wynne Hsu,
Sanjay Chawla

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: 14 August 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

National Key Research and Development Program of China
Google Faculty Research Award
Amazon Web Service (AWS) Machine Learning for Research Award
Beijing Academy of Artificial Intelligence (BAAI)

Conference

KDD '21

Sponsor:

KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

August 14 - 18, 2021

Virtual Event, Singapore

Acceptance Rates

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
846
Total Downloads

Downloads (Last 12 months)196
Downloads (Last 6 weeks)13

Reflects downloads up to 21 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Deck LSchoeffer JDe-Arteaga MKühl N(2024)A Critical Survey on Fairness Benefits of Explainable AIProceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency10.1145/3630106.3658990(1579-1595)Online publication date: 3-Jun-2024
https://dl.acm.org/doi/10.1145/3630106.3658990
Fragkathoulas CPapanikou VKaridi DPitoura E(2024)On Explaining Unfairness: An Overview2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW)10.1109/ICDEW61823.2024.00035(226-236)Online publication date: 13-May-2024
https://doi.org/10.1109/ICDEW61823.2024.00035
Mehari MSibih YDada AChang SWen PMolinaro AChukwueke UBudhu JJackson SMcFaline-Figueroa JPorter AHervey-Jumper S(2024)Enhancing neuro-oncology care through equity-driven applications of artificial intelligenceNeuro-Oncology10.1093/neuonc/noae127Online publication date: 19-Aug-2024
https://doi.org/10.1093/neuonc/noae127
Han MZhu TZhou W(2024)Fair Federated Learning with Opposite GANKnowledge-Based Systems10.1016/j.knosys.2024.111420287:COnline publication date: 16-May-2024
https://dl.acm.org/doi/10.1016/j.knosys.2024.111420
Melchiorre AMasoudian SKumar DSchedl M(2024)Modular Debiasing of Latent User Representations in Prototype-Based Recommender SystemsMachine Learning and Knowledge Discovery in Databases. Research Track10.1007/978-3-031-70341-6_4(56-72)Online publication date: 22-Aug-2024
https://doi.org/10.1007/978-3-031-70341-6_4
Ghosh BBasu DMeel K(2023)“How Biased are Your Features?”: Computing Fairness Influence Functions with Global Sensitivity AnalysisProceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency10.1145/3593013.3593983(138-148)Online publication date: 12-Jun-2023
https://dl.acm.org/doi/10.1145/3593013.3593983
Jun ISer SXu JBian JProsperi M(2023)Quantification of Racial Disparity on Urinary Tract Infection Recurrence and Treatment Resistance in Florida using Algorithmic Fairness Methods2023 IEEE 11th International Conference on Healthcare Informatics (ICHI)10.1109/ICHI57859.2023.00043(261-267)Online publication date: 26-Jun-2023
https://doi.org/10.1109/ICHI57859.2023.00043
Chen RWang JWilliamson DChen TLipkova JLu MSahai SMahmood F(2023)Algorithmic fairness in artificial intelligence for medicine and healthcareNature Biomedical Engineering10.1038/s41551-023-01056-87:6(719-742)Online publication date: 28-Jun-2023
https://doi.org/10.1038/s41551-023-01056-8
Cui SLiang JPan WChen KZhang CWang FZhang ARangwala H(2022)Collaboration Equilibrium in Federated LearningProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3534678.3539237(241-251)Online publication date: 14-Aug-2022
https://dl.acm.org/doi/10.1145/3534678.3539237
Ge YTan JZhu YXia YLuo JLiu SFu ZGeng SLi ZZhang YAmigo ECastells PGonzalo JCarterette BCulpepper JKazai G(2022)Explainable Fairness in RecommendationProceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3477495.3531973(681-691)Online publication date: 6-Jul-2022
https://dl.acm.org/doi/10.1145/3477495.3531973
Show More Cited By

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