skip to main content
10.1145/3555776.3577737acmconferencesArticle/Chapter ViewAbstractPublication PagessacConference Proceedingsconference-collections
research-article

Gradient-based Counterfactual Generation for Sparse and Diverse Counterfactual Explanations

Published: 07 June 2023 Publication History

Abstract

Counterfactual generation has attracted attention as a technique that generates samples, called counterfactual explanations, which provide a guidance to modify an input instance for changing its class label in real-world applications. Generation of multiple counterfactual explanations gives people various options to change their input instance according to their preferences or capabilities. To generate multiple counterfactual explanations, this paper proposes a gradient-based method which dynamically selects some subsets of attributes of the given instance to be tweaked for diverse counterfactual searches. It also proposes a loss-based update rule for one-hot encoded categorical attributes which is used to produce feasible and effective counterfactual explanations for instances with both categorical and continuous features. We conducted some comparative experiments on the six public datasets to evaluate the performance of the proposed method. The experiment results showed that the proposed method generates valid and diverse counterfactual explanations with a smaller number of attribute value modifications compared with the existing works.

References

[1]
S. Dandl, C. Molnar, M. Binder, and B. Bischl. 2020. Multi-Objective Counterfactual Explanations. (2020). arXiv:2004.11165
[2]
R. R. Fernandez and I. M. D. Diego. 2020. Random Forest explainability using counterfactual sets. Information Fusion 63 (2020), 196--207.
[3]
I. J. Goodfellow, J. Shlens, and C. Szegedy. 2014. Explaining and harnessing adversarial examples. (2014). arXiv:1412.6572
[4]
R. M. Grath, L. Costabello, C. L. Van, P. Sweeney, F. Kamiab, Z. Shen, and F. Lecue. 2018. Interpretable Credit Application Predictions With Counterfactual Explanations. (2018). arXiv:1811.05245
[5]
R. Guidotti, A. Monreale, S. Ruggieri, D. Pedreschi, F. Turini, and F. Giannotti. 2018. Local Rule-Based Explanations of Black Box Decision Systems. (2018). arXiv:1805.10820
[6]
H. Hofmann. 2000. UCI Machine Learning Repository. (2000). https://archive.ics.uci.edu/ml/datasets/statlog+(german+credit+data)
[7]
S. Joshi, O. Koyejo, W. Vijitbenjaronk, B. Kim, and J. Ghosh. 2019. Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems. (2019). arXiv:1907.09615
[8]
R. Kohavi and B. Becker. 1996. UCI Machine Learning Repository. (1996). https://archive.ics.uci.edu/ml/datasets/adult
[9]
I. Loshchilov and F. Hutter. 2017. Decoupled Weight Decay Regularization. (2017). arXiv:1711.05101
[10]
A. Lucic, H. Oosterhuis, H. Haned, and M. Rijke. 2022. FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles. In The Thirty-Sixth AAAI Conference on Artificial Intelligence. IEEE, 5313--5322.
[11]
D. Mahajan, C. Tan, and A. Sharma. 2019. Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers. In 33rd Conference on Neural Information Processing Systems. IEEE, 1--10.
[12]
R. K. Mothilal, A. Sharma, and C. Tan. 2020. Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations. In Conference on Fairness, Accountability, and Transparency. IEEE, 1--11.
[13]
P. Rodriguez, M. Caccia, A. Lacoste, L. Zamparo, I. Laradji, L. Charlin, and D. Vazquez. 2021. Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations. In ICCV. IEEE, 1--12.
[14]
C. Russell. 2019. Efficient Search for Diverse Coherent Explanations. (2019). arXiv:1901.04909
[15]
C. O. Sakar and Y. Kastro. 2018. UCI Machine Learning Repository. (2018). https://archive.ics.uci.edu/ml/datasets/Online+Shoppers+Purchasing+Intention+Dataset
[16]
M. Schleich, Z. Geng, Y. Zhang, and D. Suciu. 2021. GeCo: Quality Counterfactual Explanations in Real Time. (2021). arXiv:2101.01292
[17]
B. Ustun, A. Spangher, and Y. Liu. 2019. Actionable Recourse in Linear Classification. In Proceedings of the conference fairness, accountability, and transparency. ACM, 10--19.
[18]
S. Wachter, B. Mittelstadt, and C. Russell. 2018. COUNTERFACTUAL EXPLANATIONS WITHOUT OPENING THE BLACK BOX: AUTOMATED DECISIONS AND THE GDPR. Harvard Journal of Law Technology 31, 2 (2018).
[19]
I.-C. Yeh. 2009. UCI Machine Learning Repository. (2009). http://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients
[20]
H. Zhu. 2016. Predicting Earning Potential using the Adult Dataset. (2016). https://rpubs.com/H_Zhu/235617

Cited By

View all
  • (2025)Counterfactual explanations for remaining useful life estimation within a Bayesian frameworkInformation Fusion10.1016/j.inffus.2025.102972118(102972)Online publication date: Jun-2025

Index Terms

  1. Gradient-based Counterfactual Generation for Sparse and Diverse Counterfactual Explanations

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      SAC '23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing
      March 2023
      1932 pages
      ISBN:9781450395175
      DOI:10.1145/3555776
      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: 07 June 2023

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. counterfactual explanation
      2. counterfactual generation
      3. validity
      4. sparsity
      5. diversity

      Qualifiers

      • Research-article

      Conference

      SAC '23
      Sponsor:

      Acceptance Rates

      Overall Acceptance Rate 1,650 of 6,669 submissions, 25%

      Upcoming Conference

      SAC '25
      The 40th ACM/SIGAPP Symposium on Applied Computing
      March 31 - April 4, 2025
      Catania , Italy

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)41
      • Downloads (Last 6 weeks)3
      Reflects downloads up to 16 Feb 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2025)Counterfactual explanations for remaining useful life estimation within a Bayesian frameworkInformation Fusion10.1016/j.inffus.2025.102972118(102972)Online publication date: Jun-2025

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media