research-article

FACET: Robust Counterfactual Explanation Analytics

Authors:

Peter M. VanNostrand,

Dennis M. Hofmann,

Elke A. RundensteinerAuthors Info & Claims

Proceedings of the ACM on Management of Data, Volume 1, Issue 4

Article No.: 242, Pages 1 - 27

https://doi.org/10.1145/3626729

Published: 12 December 2023 Publication History

Abstract

Machine learning systems are deployed in domains such as hiring and healthcare, where undesired classifications can have serious ramifications for the user. Thus, there is a rising demand for explainable AI systems which provide actionable steps for lay users to obtain their desired outcome. To meet this need, we propose FACET, the first explanation analytics system which supports a user in interactively refining counterfactual explanations for decisions made by tree ensembles. As FACET's foundation, we design a novel type of counterfactual explanation called the counterfactual region. Unlike traditional counterfactuals, FACET's regions concisely describe portions of the feature space where the desired outcome is guaranteed, regardless of variations in exact feature values. This property, which we coin explanation robustness, is critical for the practical application of counterfactuals. We develop a rich set of novel explanation analytics queries which empower users to identify personalized counterfactual regions that account for their real-world circumstances. To process these queries, we develop a compact high-dimensional counterfactual region index along with index-aware query processing strategies for near real-time explanation analytics. We evaluate FACET against state-of-the-art explanation techniques on eight public benchmark datasets and demonstrate that FACET generates actionable explanations of similar quality in an order of magnitude less time while providing critical robustness guarantees. Finally, we conduct a preliminary user study which suggests that FACET's regions lead to higher user understanding than traditional counterfactuals.

Supplemental Material

MP4 File

Presentation video

Download
79.16 MB

PPTX File

Presentation slides

Download
4.91 MB

PPTX File

Poster

Download
5.21 MB

References

[1]

Equal Credit Opportunities Act. 1974. Public Law, 15 C.F.R § 1691, Regulation B 12 C.F.R. § 1002.

[2]

Amina Adadi and Mohammed Berrada. 2018. Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE access, Vol. 6 (2018), 52138--52160.

[3]

Solon Barocas, Andrew D. Selbst, and Manish Raghavan. 2020. The Hidden Assumptions behind Counterfactual Explanations and Principal Reasons. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (Barcelona, Spain) (FAT* '20). Association for Computing Machinery, New York, NY, USA, 80--89. https://doi.org/10.1145/3351095.3372830

Digital Library

[4]

Norbert Beckmann, Hans-Peter Kriegel, Ralf Schneider, and Bernhard Seeger. 1990. The R*-Tree: An Efficient and Robust Access Method for Points and Rectangles. In Proceedings of the 1990 ACM SIGMOD International Conference on Management of Data (Atlantic City, New Jersey, USA) (SIGMOD '90). Association for Computing Machinery, New York, NY, USA, 322--331. https://doi.org/10.1145/93597.98741

Digital Library

[5]

Stefan Berchtold, Daniel A. Keim, and Hans-Peter Kriegel. 1996. The X-Tree : An Index Structure for High-Dimensional Data. In Proceedings of the Twenty-second International Conference on Very Large Data-Bases ; Mumbai (Bombay), India 3 - 6 September, 1996, T. M. Vijayaraman (Ed.). Morgan Kaufmann, San Francisco, 28--39.

[6]

Erik Bernhardsson. 2005. Spotify/Annoy: Approximate nearest neighbors in c/python optimized for memory usage and loading/saving to disk. https://github.com/spotify/annoy.

[7]

Leo Breiman. 2001 a. Random forests. Machine learning, Vol. 45, 1 (2001), 5--32.

[8]

Leo Breiman. 2001 b. Statistical modeling: The two cultures. Statist. Sci., Vol. 16, 3 (2001), 199--231.

[9]

Zhicheng Cui, Wenlin Chen, Yujie He, and Yixin Chen. 2015. Optimal Action Extraction for Random Forests and Boosted Trees. 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, 179--188. https://doi.org/10.1145/2783258.2783281

Digital Library

[10]

Houtao Deng. 2019. Interpreting tree ensembles with intrees. International Journal of Data Science and Analytics, Vol. 7, 4 (2019), 277--287.

[11]

Amit Dhurandhar, Pin-Yu Chen, Ronny Luss, Chun-Chen Tu, Paishun Ting, Karthikeyan Shanmugam, and Payel Das. 2018. Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates, Inc., Montreal, QC, Canada, 12. https://proceedings.neurips.cc/paper/2018/file/c5ff2543b53f4cc0ad3819a36752467b-Paper.pdf

[12]

Amit Dhurandhar, Tejaswini Pedapati, Avinash Balakrishnan, Pin-Yu Chen, Karthikeyan Shanmugam, and Ruchir Puri. 2019. Model Agnostic Contrastive Explanations for Structured Data. ArXiv preprint, Vol. abs/1906.00117 (2019), 12 pages. https://arxiv.org/abs/1906.00117

[13]

Wei Dong. 2014. AAALGO/kgraph: A library for K-Nearest Neighbor Search. https://github.com/aaalgo/kgraph.

[14]

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

[15]

Sanghamitra Dutta, Jason Long, Saumitra Mishra, Cecilia Tilli, and Daniele Magazzeni. 2022. Robust Counterfactual Explanations for Tree-Based Ensembles. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, Baltimore, MD, USA, 5742--5756. https://proceedings.mlr.press/v162/dutta22a.html

[16]

Rubén R. Fernández, Isaac Martín de Diego, Víctor Aceña, Alberto Fernández-Isabel, and Javier M. Moguerza. 2020. Random forest explainability using counterfactual sets. Information Fusion, Vol. 63 (2020), 196--207. https://doi.org/10.1016/j.inffus.2020.07.001

[17]

Sainyam Galhotra, Romila Pradhan, and Babak Salimi. 2021. Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals. In Proceedings of the 2021 International Conference on Management of Data (Virtual Event, China) (SIGMOD '21). Association for Computing Machinery, New York, NY, USA, 577--590. https://doi.org/10.1145/3448016.3458455

Digital Library

[18]

Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Dino Pedreschi, Franco Turini, and Fosca Giannotti. 2018. Local Rule-Based Explanations of Black Box Decision Systems. CoRR, Vol. abs/1805.10820 (2018), 10 pages.showeprint[arXiv]1805.10820 http://arxiv.org/abs/1805.10820

[19]

Masoud Hashemi and Ali Fathi. 2020. PermuteAttack: Counterfactual Explanation of Machine Learning Credit Scorecards. https://doi.org/10.48550/ARXIV.2008.10138

[20]

Qiang Huang, Jianlin Feng, Yikai Zhang, Qiong Fang, and Wilfred Ng. 2015. Query-aware locality-sensitive hashing for approximate nearest neighbor search. Proceedings of the VLDB Endowment, Vol. 9, 1 (2015), 1--12.

Digital Library

[21]

Gregory M. Hunter and Kenneth Steiglitz. 1979. Operations on Images Using Quad Trees. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-1, 2 (1979), 145--153. https://doi.org/10.1109/TPAMI.1979.4766900

Digital Library

[22]

Qing-Yuan Jiang and Wu-Jun Li. 2015. Scalable graph hashing with feature transformation. In Twenty-fourth International Joint Conference on Artificial Intelligence. AAAI, Buenos Aires, Argentina, 2248--2254.

[23]

Kaggle. 2008. Loan Predication. https://www.kaggle.com/datasets/ninzaami/loan-predication,.

[24]

Ibrahim Kamel and Christos Faloutsos. 1993. Hilbert R-tree: An improved R-tree using fractals. Technical Report. University of Maryland, Institute for Systems Research.

[25]

Kentaro Kanamori, Takuya Takagi, Ken Kobayashi, and Hiroki Arimura. 2020. DACE: Distribution-Aware Counterfactual Explanation by Mixed-Integer Linear Optimization. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, Christian Bessiere (Ed.). International Joint Conferences on Artificial Intelligence Organization, Yokohama, Kanto, Japan, 2855--2862. https://doi.org/10.24963/ijcai.2020/395 Main track.

[26]

Amir-Hossein Karimi, Gilles Barthe, Bernhard Schölkopf, and Isabel Valera. 2022. A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations. ACM Comput. Surv., Vol. 55, 5, Article 95 (dec 2022), 29 pages. https://doi.org/10.1145/3527848

Digital Library

[27]

Amir-Hossein Karimi, Bernhard Schölkopf, and Isabel Valera. 2021. Algorithmic Recourse: From Counterfactual Explanations to Interventions. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (Virtual Event, Canada) (FAccT '21). Association for Computing Machinery, New York, NY, USA, 353--362. https://doi.org/10.1145/3442188.3445899

Digital Library

[28]

Thai Le, Suhang Wang, and Dongwon Lee. 2020. GRACE: Generating Concise and Informative Contrastive Sample to Explain Neural Network Model's Prediction. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Virtual Event, CA, USA) (KDD '20). Association for Computing Machinery, New York, NY, USA, 238--248. https://doi.org/10.1145/3394486.3403066

Digital Library

[29]

Scikit Learn. 2023. Gradient Boosting Classifier. https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingClassifier.html,.

[30]

Zhicheng Liu and Jeffrey Heer. 2014. The Effects of Interactive Latency on Exploratory Visual Analysis. IEEE Transactions on Visualization and Computer Graphics, Vol. 20, 12 (2014), 2122--2131. https://doi.org/10.1109/TVCG.2014.2346452

[31]

Ana Lucic, Harrie Oosterhuis, Hinda Haned, and Maarten de Rijke. 2022. FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, 5 (Jun. 2022), 5313--5322. https://doi.org/10.1609/aaai.v36i5.20468

[32]

Scott M Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc., Long Beach, CA, USA. https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf

[33]

Yury Malkov, Alexander Ponomarenko, Andrey Logvinov, and Vladimir Krylov. 2014. Approximate nearest neighbor algorithm based on navigable small world graphs. Information Systems, Vol. 45 (2014), 61--68.

[34]

Tim Miller. 2019. Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, Vol. 267 (2019), 1--38. https://doi.org/10.1016/j.artint.2018.07.007

[35]

Ramaravind K. Mothilal, Amit Sharma, and Chenhao Tan. 2020. Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (Barcelona, Spain) (FAT* '20). Association for Computing Machinery, New York, NY, USA, 607--617. https://doi.org/10.1145/3351095.3372850

Digital Library

[36]

Marius Muja and David G Lowe. 2014. Scalable nearest neighbor algorithms for high dimensional data. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 36, 11 (2014), 2227--2240.

[37]

Axel Parmentier and Thibaut Vidal. 2021. Optimal Counterfactual Explanations in Tree Ensembles. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, Virtual, 8422--8431. https://proceedings.mlr.press/v139/parmentier21a.html

[38]

Article 29 Data Protection Working Party. 2016. Guidelines on Automated Individual Decision-Making and Profiling for the Purposes of Regulation 2016/679. https://ec.europa.eu/newsroom/article29/items/612053

[39]

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, Vol. 12 (2011), 2825--2830.

Digital Library

[40]

Rafael Poyiadzi, Kacper Sokol, Raul Santos-Rodriguez, Tijl De Bie, and Peter Flach. 2020. FACE: Feasible and Actionable Counterfactual Explanations. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (New York, NY, USA) (AIES '20). Association for Computing Machinery, New York, NY, USA, 344--350. https://doi.org/10.1145/3375627.3375850

Digital Library

[41]

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. "Why Should I Trust You?": Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Francisco, California, USA) (KDD '16). Association for Computing Machinery, New York, NY, USA, 1135--1144. https://doi.org/10.1145/2939672.2939778

Digital Library

[42]

Omer Sagi and Lior Rokach. 2020. Explainable decision forest: Transforming a decision forest into an interpretable tree. Information Fusion, Vol. 61 (2020), 124--138.

[43]

Maximilian Schleich, Zixuan Geng, Yihong Zhang, and Dan Suciu. 2021. GeCo: Quality Counterfactual Explanations in Real Time. Proc. VLDB Endow., Vol. 14, 9 (oct 2021), 1681--1693. https://doi.org/10.14778/3461535.3461555

Digital Library

[44]

Shubham Sharma, Jette Henderson, and Joydeep Ghosh. 2020. CERTIFAI: A Common Framework to Provide Explanations and Analyse the Fairness and Robustness of Black-Box Models. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (New York, NY, USA) (AIES '20). Association for Computing Machinery, New York, NY, USA, 166--172. https://doi.org/10.1145/3375627.3375812

Digital Library

[45]

Gabriele Tolomei, Fabrizio Silvestri, Andrew Haines, and Mounia Lalmas. 2017. Interpretable Predictions of Tree-Based Ensembles via Actionable Feature Tweaking. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Halifax, NS, Canada) (KDD '17). Association for Computing Machinery, New York, NY, USA, 465--474. https://doi.org/10.1145/3097983.3098039

Digital Library

[46]

Sahil Verma, Varich Boonsanong, Minh Hoang, Keegan E. Hines, John P. Dickerson, and Chirag Shah. 2020. Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review. https://doi.org/10.48550/ARXIV.2010.10596

[47]

Sandra Wachter, Brent Mittelstadt, and Chris Russell. 2017. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. Harvard journal of law & technology, Vol. 31, 2 (2017), 841--.

Cited By

Zhang HYan BCao LMadden SRundensteiner E(2024)MetaStore: Analyzing Deep Learning Meta-Data at ScaleProceedings of the VLDB Endowment10.14778/3648160.364818217:6(1446-1459)Online publication date: 3-May-2024
https://dl.acm.org/doi/10.14778/3648160.3648182
VanNostrand PHofmann DMa LRundensteiner E(2024)Actionable Recourse for Automated Decisions: Examining the Effects of Counterfactual Explanation Type and Presentation on Lay User UnderstandingProceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency10.1145/3630106.3658997(1682-1700)Online publication date: 3-Jun-2024
https://dl.acm.org/doi/10.1145/3630106.3658997

Index Terms

FACET: Robust Counterfactual Explanation Analytics
1. Computing methodologies
  1. Artificial intelligence

Recommendations

Density-based reliable and robust explainer for counterfactual explanation
Abstract
As an essential post-hoc explanatory method, counterfactual explanation enables people to understand and react to machine learning models. Works on counterfactual explanation generally aim at generating high-quality results, which means providing ...
Causal generative explainers using counterfactual inference: a case study on the Morpho-MNIST dataset
Abstract
In this paper, we propose leveraging causal generative learning as an interpretable tool for explaining image classifiers. Specifically, we present a generative counterfactual inference approach to study the influence of visual features (pixels) ...
Counterfactual Explanations in Explainable AI: A Tutorial
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining

Deep learning has shown powerful performances in many fields, however its black-box nature hinders its further applications. In response, explainable artificial intelligence emerges, aiming to explain the predictions and behaviors of deep learning ...

Comments

Information & Contributors

Information

Published In

cover image Proceedings of the ACM on Management of Data

Proceedings of the ACM on Management of Data Volume 1, Issue 4

PACMMOD

December 2023

1317 pages

EISSN:2836-6573

DOI:10.1145/3637468

Editor:
Divyakant Agrawal
UC Santa Barbara, United States

Issue’s Table of Contents

Copyright © 2023 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 the author(s) 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].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 12 December 2023

Published in PACMMOD Volume 1, Issue 4

Permissions

Request permissions for this article.

Request Permissions

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
240
Total Downloads

Downloads (Last 12 months)240
Downloads (Last 6 weeks)34

Reflects downloads up to 17 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Zhang HYan BCao LMadden SRundensteiner E(2024)MetaStore: Analyzing Deep Learning Meta-Data at ScaleProceedings of the VLDB Endowment10.14778/3648160.364818217:6(1446-1459)Online publication date: 3-May-2024
https://dl.acm.org/doi/10.14778/3648160.3648182
VanNostrand PHofmann DMa LRundensteiner E(2024)Actionable Recourse for Automated Decisions: Examining the Effects of Counterfactual Explanation Type and Presentation on Lay User UnderstandingProceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency10.1145/3630106.3658997(1682-1700)Online publication date: 3-Jun-2024
https://dl.acm.org/doi/10.1145/3630106.3658997

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 Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents