The DOI matches its Crossref record; 38 of the 39 references it cites were found in a registry or an index.
On generating trustworthy counterfactual explanations
Open accessAbstract
Deep learning models like chatGPT exemplify AI success but necessitate a deeper understanding of trust in critical sectors. Trust can be achieved using counterfactual explanations, which is how humans become familiar with unknown processes; by understanding the hypothetical input circumstances under which the output changes. We argue that the generation of counterfactual explanations requires several aspects of the generated counterfactual instances, not just their counterfactual ability. We present a framework for generating counterfactual explanations that formulate its goal as a multiobjective optimization problem balancing three objectives: plausibility; the intensity of changes; and adversarial power. We use a generative adversarial network to model the distribution of the input, along with a multiobjective counterfactual discovery solver balancing these objectives. We demonstrate the usefulness of six classification tasks with image and 3D data confirming with evidence the existence of a trade-off between the objectives, the consistency of the produced counterfactual explanations with human knowledge, and the capability of the framework to unveil the existence of concept-based biases and misrepresented attributes in the input domain of the audited model. Our pioneering effort shall inspire further work on the generation of plausible counterfactual explanations in real-world scenarios where attribute-/concept-based annotations are available for the domain under analysis.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The study demonstrates across six classification tasks using image and 3D data confirm evidence of trade-offs between objectives and consistency of the generated explanations with human understanding, and the framework's ability to reveal concept-based biases and misrepresented attributes within the model's input domain.”
From Recent Emerging Techniques in Explainable Artificial Intelligence to Enhance the Interpretable and Understanding of AI Models for Human (2025) · cites this paper as [34]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Self-citationDeep Learning Face Attributes in the Wild
Liu, Z., Luo, P., Wang, X., & Tang, X. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.425 · Cited by 7,747
2009 IEEE Conference on Computer Vision and Pattern Recognition
(2009) · doi:10.1109/cvpr14067.2009 · Cited by 5,646
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524
Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
Breiman, L. (2001) · Statistical Science · doi:10.1214/ss/1009213726 · Cited by 4,340
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks
Chattopadhay, A., Sarkar, A., Howlader, P., & Balasubramanian, V. N. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00097 · Cited by 3,639
A survey of uncertainty in deep neural networks
Gawlikowski, J., Tassi, C. R. N., Ali, M., Lee, J., Humt, M., Feng, J., Kruspe, A., Triebel, R., Jung, P., Roscher, R., et al. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10562-9 · Cited by 1,670
Roese, N. J. (1997) · Psychological Bulletin · doi:10.1037/0033-2909.121.1.133 · Cited by 1,156
Counterfactual explanations without opening the black box: automated decisions and the GDPR
Wachter, S., Mittelstadt, B., & Russell, C. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3063289 · Cited by 1,061
AttGAN: Facial attribute editing by only changing what you want
He, Z., Zuo, W., Kan, M., Shan, S., & Chen, X. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2916751 · Cited by 833
The master algorithm: how the quest for the ultimate learning machine will remake our world
(2016) · Choice Reviews Online · doi:10.5860/choice.194685 · Cited by 810
Deep learning approach for active classification of electrocardiogram signals
Rahhal, M. M. A., Bazi, Y., Alhichri, H. S., Alajlan, N., Melgani, F., & Yager, R. R. (2016) · Information Sciences · doi:10.1016/j.ins.2016.01.082 · Cited by 626
Actionable Recourse in Linear Classification
Ustun, B., Spangher, A., & Liu, Y. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287566 · Cited by 501
AI for life: Trends in artificial intelligence for biotechnology
Holzinger, A., Keiblinger, K., Holub, P., Zatloukal, K., & Müller, H. (2023) · New Biotechnology · doi:10.1016/j.nbt.2023.02.001 · Cited by 438
Self-citationSchwalbe, G., & Finzel, B. (2023) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00867-8 · Cited by 422
International Conference on Computer Vision（ICCV '95）
阿部圭一 (1995) · Cited by 388
Stepin, I., Alonso, J. M., Catala, A., & Pereira-Farina, M. (2021) · IEEE Access · doi:10.1109/access.2021.3051315 · Cited by 376
2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
(2018) · doi:10.1109/wacv41190.2018 · Cited by 350
FACE: Feasible and Actionable Counterfactual Explanations
Poyiadzi, R., Sokol, K., Santos-Rodriguez, R., De Bie, T., & Flach, P. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375850 · Cited by 317
Counterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning
Byrne, R. M. J. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/876 · Cited by 285
jMetalPy: A Python framework for multi-objective optimization with metaheuristics
Benítez‐Hidalgo, A., Nebro, A. J., García-Nieto, J., Oregi, I., & Ser, J. D. (2019) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2019.100598 · Cited by 257
Holzinger, A., Saranti, A., Angerschmid, A., Retzlaff, C. O., Gronauer, A., Pejaković, V., Medel-Jiménez, F., Krexner, T., Gollob, C., & Stampfer, K. (2022) · Sensors · doi:10.3390/s22083043 · Cited by 225
Self-citationModel-Agnostic Counterfactual Explanations for Consequential DecisionsPreprint
Karimi, A.-H., Barthe, G., Balle, B., & Valera, I. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.11190 · Cited by 212
2022 ACM Conference on Fairness Accountability and Transparency
(2022) · doi:10.1145/3531146 · Cited by 148
Cognitive neuroscience of human counterfactual reasoning
Hoeck, N. V. (2015) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2015.00420 · Cited by 147
On Counterfactual Explanations under Predictive MultiplicityPreprint
Pawelczyk, M., Broelemann, K., & Kasneci, G. (2020) · Conference on Uncertainty in Artificial Intelligence · doi:10.48550/arxiv.2006.13132 · Cited by 106
Toward Human–AI Interfaces to Support Explainability and Causability in Medical AI
Holzinger, A., & Müller, H. (2021) · Computer · doi:10.1109/mc.2021.3092610 · Cited by 99
Self-citationPredictive Multiplicity in ClassificationPreprint
Marx, C. T., Calmon, F. P., & Ustun, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06677 · Cited by 56
Toward human-level concept learning: Pattern benchmarking for AI algorithms
Holzinger, A., Saranti, A., Angerschmid, A., Finzel, B., Schmid, U., & Mueller, H. (2023) · Patterns · doi:10.1016/j.patter.2023.100788 · Cited by 54
Self-citationThe Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World.
Domingos, P. (2015) · Journal of Computer Science and Technology · Cited by 34
The Use and Misuse of Counterfactuals in Ethical Machine Learning
Kasirzadeh, A., & Smart, A. (2021) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3442188.3445886 · Cited by 27
Concept Activation Regions: A Generalized Framework for Concept-Based Explanations
Crabbé, J., & Schaar, M. V. D. (2022) · neural information processing systems · doi:10.52202/068431-0188 · Cited by 27
Saranti, A., Hudec, M., Mináriková, E., Takáč, Z., Großschedl, U., Koch, C., Pfeifer, B., Angerschmid, A., & Holzinger, A. (2022) · Machine Learning and Knowledge Extraction · doi:10.3390/make4040047 · Cited by 25
Self-citationConcept Activation Regions: A Generalized Framework For Concept-Based ExplanationsPreprint
Crabbé, J., & van der Schaar, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2209.11222 · Cited by 16
Cited by
Sorted by citations
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Ser, J. D., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., et al. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102301 · Cited by 626
Self-citationŞahin, E., Arslan, N. N., & Özdemir, D. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10437-2 · Cited by 358
Mienye, I. D., Obaido, G., Jere, N., Mienye, E., Aruleba, K., Emmanuel, I. D., & Ogbuokiri, B. (2024) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2024.101587 · Cited by 212
Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists
Retzlaff, C. O., Angerschmid, A., Saranti, A., Schneeberger, D. M., Röttger, R., Müller, H., & Holzinger, A. (2024) · Cognitive Systems Research · doi:10.1016/j.cogsys.2024.101243 · Cited by 229
Self-citationHuman-Centered AI in Smart Farming: Toward Agriculture 5.0
Holzinger, A., Fister, I., Fister, I., Kaul, H., & Asseng, S. (2024) · IEEE Access · doi:10.1109/access.2024.3395532 · Cited by 223
Self-citation
Metadata
- Authors
- Del Ser, J., Barredo-Arrieta, A., Díaz-Rodríguez, N., Herrera, F., Saranti, A., & Holzinger, A.
- Affiliations
- Universidad de Granada (ES)
- Medical University of Graz (AT)
- Corresponding author
- Holzinger, Andreas
- Venue
- Information Sciences
- Publisher
- Elsevier BV
- Published
- 2024-01
- Volume
- 655
- Pages
- 119898
- ISSN
- 0020-0255 (ISSN-L)
- OpenAlex
- W4388767362
- Cited by
- 122
- References
- 39
- Citations by year
- 2026: 22 · 2025: 49 · 2024: 51
- FWCI
- 11.49
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Information Sciences (publishedVersion, cc-by)
- Institutional Repository of the University of Granada (University of Granada) (submittedVersion, cc-by)
- TECNALIA Publications (Fundación TECNALIA Research & Innovation) (submittedVersion, public-domain)
- Funders
- European Commission (CER-20211030)
- Horizon 2020 (826078)
- Austrian Science Fund (P-32554)
- H2020 Marie Skłodowska-Curie Actions (101059332)
- Centro para el Desarrollo Tecnológico Industrial
- Eusko Jaurlaritza (IT1256-22)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Keywords
- counterfactual explanations, trustworthy AI, multi-objective optimization, generative adversarial networks, plausibility, explainable deep learning, image classification
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
