The DOI matches its Crossref record; 254 of the 254 references it cites were found in a registry or an index.
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Open accessAbstract
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understandable way, the relationship between the input and output of machine learning models is essential to the development of trustworthy machine learning based systems. A burgeoning body of research seeks to define the goals and methods of explainability in machine learning. In this article, we seek to review and categorize research on counterfactual explanations , a specific class of explanation that provides a link between what could have happened had input to a model been changed in a particular way. Modern approaches to counterfactual explainability in machine learning draw connections to the established legal doctrine in many countries, making them appealing to fielded systems in high-impact areas such as finance and healthcare. Thus, we design a rubric with desirable properties of counterfactual explanation algorithms and comprehensively evaluate all currently proposed algorithms against that rubric. Our rubric provides easy comparison and comprehension of the advantages and disadvantages of different approaches and serves as an introduction to major research themes in this field. We also identify gaps and discuss promising research directions in the space of counterfactual explainability.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Items 201–254 of 254
On Quantitative Evaluations of CounterfactualsPreprint
Hvilshøj, F., Iosifidis, A., & Assent, I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.00177 · Cited by 14
Explaining Deep Graph Networks via Input Perturbation
Bacciu, D., & Numeroso, D. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3165618 · Cited by 14
Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics
USA, S. I. C. O. M. O. D. 2. C. I., Association for Computing Machinery-Digital Library, ACM Special Interest Group on Management of Data, & SIGs, A. (2017) · doi:10.1145/3077257 · Cited by 14
Tsiakmaki, M., & Ragos, O. (2021) · International Conference on Circuits, Systems, Communications and Computers (CSCC) · doi:10.1109/cscc53858.2021.00029 · Cited by 13
Exploring Counterfactual Explanations for Classification and Regression Trees
Hada, S. S., & Carreira-Perpiñán, M. Á. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-93736-2_37 · Cited by 13
Interactivity, Fairness and Explanations in Recommendations
Giannopoulos, G., Papastefanatos, G., Sacharidis, D., & Stefanidis, K. (2021) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3450614.3462238 · Cited by 12
Diffusion Models for Counterfactual ExplanationsPreprint
Jeanneret, G., Simon, L., & Jurie, F. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.15636 · Cited by 12
An exact counterfactual-example-based approach to tree-ensemble models interpretabilityPreprint
Blanchart, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.14820 · Cited by 11
Improving users' mental model with attention‐directed counterfactual edits
Alipour, K., Ray, A., Lin, X., Cogswell, M., Schulze, J. P., Yao, Y., & Burachas, G. (2021) · Applied AI Letters · doi:10.1002/ail2.47 · Cited by 11
DeDUCE: Generating Counterfactual Explanations EfficientlyPreprint
Höltgen, B. T. A., Schut, L., Brauner, J., & Gal, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.15639 · Cited by 11
Automated Counterfactual Generation in Financial Model Risk Management
Gan, J., Zhang, S., Zhang, C., & Li, A. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671561 · Cited by 11
Post-hoc Counterfactual Generation with Supervised Autoencoder
Guyomard, V., Fessant, F., Bouadi, T., & Guyet, T. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-93736-2_10 · Cited by 11
From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender SystemsPreprint
Zhou, Y., Wang, H., He, J., & Wang, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.14844 · Cited by 10
Mining Pareto-optimal counterfactual antecedents with a branch-and-bound model-agnostic algorithm
Raimundo, M. M., Nonato, L. G., & Poco, J. (2022) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00906-4 · Cited by 10
Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks
Nemirovsky, D., Thiébaut, N., Xu, Y., & Gupta, A. (2021) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3437963.3441705 · Cited by 9
Contrastive Explanations for Explaining Model Adaptations
Artelt, A., Hinder, F., Vaquet, V., Feldhans, R., & Hammer, B. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-85030-2_9 · Cited by 9
Developing and Experimenting on Approaches to Explainability in AI Systems
Zhang, Y., McAreavey, K., & Liu, W. (2022) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0010900300003116 · Cited by 9
Crupi, R., González, B. S. M., Castelnovo, A., & Regoli, D. (2022) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0010761500003116 · Cited by 9
Counterfactual Explanations for Natural Language Interfaces
Tolkachev, G., Mell, S., Zdancewic, S. A., & Bastani, O. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-short.14 · Cited by 9
Convex optimization for actionable \& plausible counterfactual explanationsPreprint
Artelt, A., & Hammer, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.07630 · Cited by 9
Magrini, A., Blasi, S., & Stefanini, F. M. (2017) · Biometrical Letters · doi:10.1515/bile-2017-0002 · Cited by 8
Counterfactual Generation with KnockoffsPreprint
Popescu, O.-I., Shadaydeh, M., & Denzler, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.00951 · Cited by 8
Enhancing the Value of Counterfactual Explanations for Deep Learning
Jia, Y., McDermid, J. A., & Habli, I. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77211-6_46 · Cited by 8
Persuasive Contrastive Explanations for Bayesian Networks
Koopman, T., & Renooij, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86772-0_17 · Cited by 8
Influence-Driven Explanations for Bayesian Network Classifiers
Albini, E., Rago, A., Baroni, P., & Toni, F. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89188-6_7 · Cited by 8
Counterfactual attribute-based visual explanations for classification
Gulshad, S., & Smeulders, A. W. M. (2021) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-021-00208-3 · Cited by 7
Ordered Counterfactual Explanation by Mixed-Integer Linear Optimization
Kanamori, K., Takagi, T., Kobayashi, K., Ike, Y., Uemura, K., & Arimura, H. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i13.17376 · Cited by 7
Refined Core Relaxation for Core-Guided MaxSAT Solving
Ihalainen, H., Berg, J., & Järvisalo, M. (2021) · Työväentutkimus Vuosikirja · doi:10.4230/lipics.cp.2021.28 · Cited by 7
Becker, M., Burkart, N., Birnstill, P., & Beyerer, J. (2021) · Advances in Artificial Intelligence and Machine Learning · doi:10.54364/aaiml.2021.1107 · Cited by 7
Analyzing and Improving the Robustness of Tabular Classifiers using Counterfactual Explanations
Rasouli, P., & Yu, I. C. (2021) · International Conference on Machine Learning and Applications · doi:10.1109/icmla52953.2021.00209 · Cited by 7
Counterfactual Explanations of Concept DriftPreprint
Hinder, F., & Hammer, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.12822 · Cited by 6
Multi-Agent Algorithmic RecoursePreprint
O’Brien, A., & Kim, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.00673 · Cited by 6
Improving Algorithmic Decision–Making in the Presence of Untrustworthy Training Data
Qi, W., & Chelmis, C. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671677 · Cited by 6
Counterfactual explanation of Bayesian model uncertainty
Ali, G., Al-Obeidat, F. N., Tubaishat, A., Zia, T., Ilyas, M., & Rocha, Á. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06528-z · Cited by 5
Counterfactual Plans under Distributional AmbiguityPreprint
Bui, N. T.-N., Nguyen, D., & Nguyen, V. A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.12487 · Cited by 5
Mitigating the Rashomon Effect in Counterfactual Explanation: A Game-theoretic Approach
Hasan, M. G. M. M., & Talbert, D. A. (2022) · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference · doi:10.32473/flairs.v35i.130711 · Cited by 5
Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's DecisionPreprint
Oh, K., Yoon, J. S., & Suk, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.10381 · Cited by 4
Model-Agnostic Explanations using Minimal Forcing Subsets
Han, X., & Ghosh, J. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533992 · Cited by 4
DCFG: Discovering Directional CounterFactual Generation for Chest X-rays
Li, Y., Liu, S., Wu, C., Xi, X., Cao, G., & Cao, W. (2021) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm52615.2021.9669770 · Cited by 4
Counterfactually Evaluating Explanations in Recommender SystemsPreprint
Yao, Y., Wang, C., & Li, H. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.01310 · Cited by 4
Selection, Ignorability and Challenges With Causal FairnessPreprint
Fawkes, J., Evans, R. J., & Sejdinović, D. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.13774 · Cited by 4
Semi-factual Explanations in AI
Aryal, S. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i21.30390 · Cited by 4
The Uncertainty of Counterfactuals in Deep Learning
Brown, K. E., Talbert, D. A., & Talbert, S. (2021) · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference · doi:10.32473/flairs.v34i1.128795 · Cited by 3
Fdez-Sánchez, J. A., Pascual-Triana, J. D., Fernández, A., & Herrera, F. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.097 · Cited by 3
Deriving Explainable Discriminative Attributes Using Confusion About Counterfactual Class
Yang, N., Kang, T., & Jung, K. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747693 · Cited by 3
COIN: Counterfactual Image Generation for VQA InterpretationPreprint
Boukhers, Z., Hartmann, T., & Jürjens, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.03342 · Cited by 3
Data Augmentation using Counterfactuals: Proximity vs Diversity
Hasan, M. G. M. M., & Talbert, D. A. (2022) · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference · doi:10.32473/flairs.v35i.130705 · Cited by 3
Gradient-based Counterfactual Explanations using Tractable Probabilistic ModelsPreprint
Shao, X., & Kersting, K. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.07774 · Cited by 3
Multi-Domain Transformer-Based Counterfactual Augmentation for Earnings Call AnalysisPreprint
Yuan, Z., Zhu, Y., Zhang, W., Huang, Z., Ye, G., & Xiong, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.00963 · Cited by 2
Inverse Classification with Limited Budget and Maximum Number of Perturbed SamplesPreprint
Koo, J., Klabjan, D., & Utke, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.14111 · Cited by 1
A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular DataPreprint
Oliveira, R., & Martens, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.04680 · Cited by 1
Beyond Trivial Counterfactual Explanations with Diverse Valuable ExplanationsPreprint
Rodríguez, P., Caccia, M., Lacoste, A., Zamparo, L., Laradji, I., Charlin, L., & Vázquez, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.10226 · Cited by 1
Beyond Explanations: Recourse via Actionable Interpretability - Extended
Tahoun, E., & Kassis, A. (2020) · doi:10.13140/rg.2.2.19076.14729 · Cited by 1
Finding Counterfactual Explanations through Constraint RelaxationsPreprint
Gupta, S. D., Genç, B., & O'Sullivan, B. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2204.03429 · Cited by 1
Cited by
Interpretable and Explainable Machine Learning for Materials Science and Chemistry
Oviedo, F., Ferres, J. L., Buonassisi, T., & Butler, K. T. (2022) · Accounts of Materials Research · doi:10.1021/accountsmr.1c00244 · Cited by 435
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Verma, S., Boonsanong, V., Hoang, M., Hines, K. E., Dickerson, J. P., & Shah, C. (2020) · arXiv · doi:10.48550/arxiv.2010.10596 · Cited by 267
Self-citationEXplainable Artificial Intelligence (XAI)—From Theory to Methods and Applications
Ortigossa, E. S., Gonçalves, T., & Nonato, L. G. (2024) · IEEE Access · doi:10.1109/access.2024.3409843 · Cited by 124
McNamara, S. L., Yi, P. H., & Lotter, W. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01080-1 · Cited by 60
Hasan, R., Dattana, V., Mahmood, S., & Hussain, S. (2024) · Information · doi:10.3390/info16010007 · Cited by 44
Metadata
- Authors
- Verma, S., Boonsanong, V., Hoang, M., Hines, K., Dickerson, J., & Shah, C.
- Venue
- ACM Computing Surveys
- Published
- 2024-10-03
- Volume
- 56
- Issue
- 12
- Pages
- 1-42
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4400461591
- Cited by
- 255
- References
- 254
- FWCI
- 34.08
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.