research-article

Promoting Fairness in Learned Models by Learning to Active Learn under Parity Constraints

Authors:

Renkun NiAuthors Info & Claims

FAccT '22: Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency

Pages 2149 - 2156

https://doi.org/10.1145/3531146.3534632

Published: 20 June 2022 Publication History

Abstract

Machine learning models can have consequential effects when used to automate decisions, and disparities between groups of people in the error rates of those decisions can lead to harms suffered more by some groups than others. Past algorithmic approaches aim to enforce parity across groups given a fixed set of training data; instead, we ask: what if we can gather more data to mitigate disparities? We develop a meta-learning algorithm for parity-constrained active learning that learns a policy to decide which labels to query so as to maximize accuracy subject to parity constraints. To optimize the active learning policy, our proposed algorithm formulates the parity-constrained active learning task as a bi-level optimization problem. The inner level corresponds to training a classifier on a subset of labeled examples. The outer level corresponds to updating the selection policy choosing this subset to achieve a desired fairness and accuracy behavior on the trained classifier. To solve this constrained bi-level optimization problem, we employ the Forward-Backward Splitting optimization method. Empirically, across several parity metrics and classification tasks, our approach outperforms alternatives by a large margin.

References

[1]

Behnoush Abdollahi and Olfa Nasraoui. 2018. Transparency in fair machine learning: The case of explainable recommender systems. In Human and Machine Learning. Springer, Springer, 21–35.

[2]

Alekh Agarwal, Alina Beygelzimer, Miroslav Dudik, John Langford, and Hanna Wallach. 2018. A Reductions Approach to Fair Classification. In Proceedings of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). PMLR, USA, 60–69. https://proceedings.mlr.press/v80/agarwal18a.html

[3]

Hadis Anahideh, Abolfazl Asudeh, and Saravanan Thirumuruganathan. 2022. Fair active learning. Expert Systems with Applications 199 (2022), 116981. https://doi.org/10.1016/j.eswa.2022.116981

Digital Library

[4]

Dana Angluin. 1988. Queries and Concept Learning. Mach. Learn. 2, 4 (April 1988), 319–342. https://doi.org/10.1023/A:1022821128753

Digital Library

[5]

Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine bias. ProPublica.

[6]

Philip Bachman, Alessandro Sordoni, and Adam Trischler. 2017. Learning Algorithms for Active Learning. In Proceedings of the 34th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 70), Doina Precup and Yee Whye Teh (Eds.). PMLR, PMLR, 301–310. https://proceedings.mlr.press/v70/bachman17a.html

[7]

Michelle Bao, Angela Zhou, Samantha Zottola, Brian Brubach, Sarah Desmarais, Aaron Horowitz, Kristian Lum, and Suresh Venkatasubramanian. 2021. It’s COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks.

[8]

Ángel Alexander Cabrera, Will Epperson, Fred Hohman, Minsuk Kahng, Jamie Morgenstern, and Duen Horng Chau. 2019. FairVis: Visual analytics for discovering intersectional bias in machine learning.

[9]

Irene Y. Chen, Fredrik D. Johansson, and David Sontag. 2018. Why is My Classifier Discriminatory?. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (Montréal, Canada) (NIPS’18). Curran Associates Inc., Red Hook, NY, USA, 3543–3554.

Digital Library

[10]

Alexandra Chouldechova. 2017. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big data 5, 2 (2017), 153–163.

[11]

David Cohn, Les Atlas, and Richard Ladner. 1994. Improving generalization with active learning. Machine learning 15, 2 (1994), 201–221.

[12]

Patrick L Combettes and Valérie R Wajs. 2005. Signal recovery by proximal forward-backward splitting. Multiscale Modeling & Simulation 4, 4 (2005), 1168–1200.

[13]

Kate Crawford and Ryan Calo. 2016. There is a blind spot in AI research. Nature 538, 7625 (2016), 311–313.

[14]

Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc V Le, and Ruslan Salakhutdinov. 2019. Transformer-xl: Attentive language models beyond a fixed-length context.

[15]

Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, and Łukasz Kaiser. 2018. Universal transformers.

[16]

Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding.

[17]

Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. http://archive.ics.uci.edu/ml

[18]

Meng Fang, Yuan Li, and Trevor Cohn. 2017. Learning how to active learn: A deep reinforcement learning approach.

[19]

Valerii Vadimovich Fedorov. 2013. Theory of optimal experiments.

[20]

Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian. 2015. Certifying and Removing Disparate Impact. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Sydney, NSW, Australia) (KDD ’15). Association for Computing Machinery, New York, NY, USA, 259–268. https://doi.org/10.1145/2783258.2783311

Digital Library

[21]

Batya Friedman and Helen Nissenbaum. 1996. Bias in computer systems. ACM Transactions on Information Systems (TOIS) 14, 3 (1996), 330–347.

Digital Library

[22]

Sainyam Galhotra, Yuriy Brun, and Alexandra Meliou. 2017. Fairness testing: Testing software for discrimination.

[23]

Vivian Giang. 2018. The potential hidden bias in automated hiring systems.

[24]

Tom Goldstein, Christoph Studer, and Richard Baraniuk. 2014. A field guide to forward-backward splitting with a FASTA implementation.

[25]

Emil Julius Gumbel. 1948. Statistical theory of extreme values and some practical applications: a series of lectures.

[26]

Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning., 3315–3323 pages.

[27]

Kenneth Holstein, Jennifer Wortman Vaughan, Hal Daumé III, Miro Dudik, and Hanna Wallach. 2019. Improving fairness in machine learning systems: What do industry practitioners need?, 16 pages.

[28]

Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax.

[29]

Jun Jiang and Horace Ho-Shing Ip. 2008. Active learning for the prediction of phosphorylation sites., 3158–3165 pages.

[30]

Nathan Kallus and Angela Zhou. 2018. Residual unfairness in fair machine learning from prejudiced data.

[31]

Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization.

[32]

Jon Kleinberg, Sendhil Mullainathan, and Manish Raghavan. 2016. Inherent trade-offs in the fair determination of risk scores.

[33]

Ksenia Konyushkova, Raphael Sznitman, and Pascal Fua. 2017. Learning active learning from data., 4225–4235 pages.

[34]

Wouter Kool, Herke Van Hoof, and Max Welling. 2019. Stochastic beams and where to find them: The gumbel-top-k trick for sampling sequences without replacement.

[35]

Pierre-Louis Lions and Bertrand Mercier. 1979. Splitting algorithms for the sum of two nonlinear operators. SIAM J. Numer. Anal. 16, 6 (1979), 964–979.

Digital Library

[36]

Chris J Maddison, Andriy Mnih, and Yee Whye Teh. 2016. The concrete distribution: A continuous relaxation of discrete random variables.

[37]

Arvind Narayanan. 2018. Translation tutorial: 21 fairness definitions and their politics.

[38]

Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library., 8024–8035 pages. http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf

Digital Library

[39]

Piyush Rai, Avishek Saha, Hal Daumé III, and Suresh Venkatasubramanian. 2010. Domain adaptation meets active learning., 27–32 pages.

[40]

Dan Roth and Kevin Small. 2006. Margin-based active learning for structured output spaces., 413–424 pages.

[41]

Burr Settles. 2009. Active learning literature survey. Technical Report. University of Wisconsin-Madison Department of Computer Sciences.

[42]

Claude E Shannon. 1948. A note on the concept of entropy. Bell System Tech. J 27, 3 (1948), 379–423.

[43]

Xiaoxiao Shi, Wei Fan, and Jiangtao Ren. 2008. Actively transfer domain knowledge., 342–357 pages.

[44]

Megha Srivastava, Hoda Heidari, and Andreas Krause. 2019. Mathematical notions vs. human perception of fairness: A descriptive approach to fairness for machine learning., 2459–2468 pages.

[45]

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need., 5998–6008 pages.

[46]

Michael Veale and Reuben Binns. 2017. Fairer machine learning in the real world: Mitigating discrimination without collecting sensitive data. Big Data & Society 4, 2 (2017), 2053951717743530.

[47]

Tim Vieira. 2014. Gumbel-max trick and weighted reservoir sapling. (2014). https://timvieira.github.io/blog/post/2014/08/01/gumbel-max-trick-and-weightedreservoir-sampling/.

[48]

Sara Wachter-Boettcher. 2017. AI recruiting tools do not eliminate bias.

[49]

Xuezhi Wang, Tzu-Kuo Huang, and Jeff Schneider. 2014. Active Transfer Learning under Model Shift. In Proceedings of the 31st International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 32), Eric P. Xing and Tony Jebara (Eds.). PMLR, Bejing, China, 1305–1313. https://proceedings.mlr.press/v32/wangi14.html

[50]

L. Wightman. 1998. LSAC National Longitudinal Bar Passage Study. (1998). LSAC.

[51]

Benjamin Wilson, Judy Hoffman, and Jamie Morgenstern. 2019. Predictive inequity in object detection.

[52]

Tal Zarsky. 2016. The trouble with algorithmic decisions: An analytic road map to examine efficiency and fairness in automated and opaque decision making. Science, Technology, & Human Values 41, 1 (2016), 118–132.

Cited By

Sonoda RSrinivasan R(2024)Mutual Information-Based Fair Active LearningICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)10.1109/ICASSP48485.2024.10446623(4965-4969)Online publication date: 14-Apr-2024
https://doi.org/10.1109/ICASSP48485.2024.10446623
Fajri RSaxena APei YPechenizkiy M(2024)FAL-CURExpert Systems with Applications: An International Journal10.1016/j.eswa.2023.122842242:COnline publication date: 16-May-2024
https://dl.acm.org/doi/10.1016/j.eswa.2023.122842
Singh HChunara R(2023)Measures of Disparity and their Efficient EstimationProceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society10.1145/3600211.3604697(927-938)Online publication date: 8-Aug-2023
https://dl.acm.org/doi/10.1145/3600211.3604697
Show More Cited By

Index Terms

Promoting Fairness in Learned Models by Learning to Active Learn under Parity Constraints
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches
2. Theory of computation

Index terms have been assigned to the content through auto-classification.

Recommendations

Active learning and data manipulation techniques for generating training examples in meta-learning

Algorithm selection is an important task in different domains of knowledge. Meta-learning treats this task by adopting a supervised learning strategy. Training examples in meta-learning (called meta-examples) are generated from experiments performed ...
Combining active learning and semi-supervised for improving learning performance
ISABEL '11: Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies

In many learning tasks, there are abundant unlabeled samples but the number of labeled training samples is limited, because labeling the samples requires the efforts of human annotators and expertise. There are three major techniques for labeling the ...
Multiple-view multiple-learner active learning

Generally, collecting a large quantity of unlabeled examples is feasible, but labeling them all is not. Active learning can reduce the number of labeled examples needed to train a good classifier. Existing active learning algorithms can be roughly ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

FAccT '22: Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency

June 2022

2351 pages

ISBN:9781450393522

DOI:10.1145/3531146

Copyright © 2022 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

ACM: Association for Computing Machinery

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 20 June 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

FAccT '22

Sponsor:

ACM

FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency

June 21 - 24, 2022

Seoul, Republic of Korea

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
281
Total Downloads

Downloads (Last 12 months)81
Downloads (Last 6 weeks)2

Reflects downloads up to 12 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Sonoda RSrinivasan R(2024)Mutual Information-Based Fair Active LearningICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)10.1109/ICASSP48485.2024.10446623(4965-4969)Online publication date: 14-Apr-2024
https://doi.org/10.1109/ICASSP48485.2024.10446623
Fajri RSaxena APei YPechenizkiy M(2024)FAL-CURExpert Systems with Applications: An International Journal10.1016/j.eswa.2023.122842242:COnline publication date: 16-May-2024
https://dl.acm.org/doi/10.1016/j.eswa.2023.122842
Singh HChunara R(2023)Measures of Disparity and their Efficient EstimationProceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society10.1145/3600211.3604697(927-938)Online publication date: 8-Aug-2023
https://dl.acm.org/doi/10.1145/3600211.3604697
Wu TSu HChen SHsu W(2023)Fair Robust Active Learning by Joint Inconsistency2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)10.1109/ICCVW60793.2023.00390(3624-3633)Online publication date: 2-Oct-2023
https://doi.org/10.1109/ICCVW60793.2023.00390
Liu ZZhang XJiang B(2023)Active learning with fairness-aware clustering for fair classification considering multiple sensitive attributesInformation Sciences: an International Journal10.1016/j.ins.2023.119521647:COnline publication date: 1-Nov-2023
https://dl.acm.org/doi/10.1016/j.ins.2023.119521
Cao YLan C(2022)Fairness-Aware Active Learning for Decoupled Model2022 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN55064.2022.9892608(1-9)Online publication date: 18-Jul-2022
https://doi.org/10.1109/IJCNN55064.2022.9892608

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.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents