Relation-Based Counterfactual Explanations for Bayesian Network Classifiers
Open accessAbstract
We propose a general method for generating counterfactual explanations (CFXs) for a range of Bayesian Network Classifiers (BCs), e.g. single- or multi-label, binary or multidimensional. We focus on explanations built from relations of (critical and potential) influence between variables, indicating the reasons for classifications, rather than any probabilistic information. We show by means of a theoretical analysis of CFXs’ properties that they serve the purpose of indicating (potentially) pivotal factors in the classification process, whose absence would give rise to different classifications. We then prove empirically for various BCs that CFXs provide useful information in real world settings, e.g. when race plays a part in parole violation prediction, and show that they have inherent advantages over existing explanation methods in the literature.
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
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.
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?
Besides using Incremental Deletion/Addition to evaluate correctness and output-completeness, compactness can be evaluated by counting how many features of the explanation need to be removed, perturbed or added to change the decision of the predictive model.
“Besides using Incremental Deletion/Addition to evaluate correctness and output-completeness, compactness can be evaluated by counting how many features of the explanation need to be removed, perturbed or added to change the decision of the predictive model [7,34,70,123,165,221].”
From From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2023) · cites this paper as [7]
Examples of compactness metrics include the number of features in an explanation, average path length in a decision tree, reduction with respect to the complete data sample, and the number of decision rules in a set.
“Examples include: the number of features in an explanation (e.g., [54,109,192,204,223,265]), average path length in a decision tree (e.g., [135,276,277]), reduction w.r.t.complete data sample (e.g., [7,33,109]), or the number of decision rules in a set (e.g., [137,144,203,223,266,302]).”
From From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2023) · cites this paper as [7]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · see citing works
Gauriat, C.-M., Pencolé, Y., Ribot, P., et al. (2024) · HAL · doi:10.4230/oasics.dx.2024.27 · Cited by 12,623 · see citing works
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682 · see citing works
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302 · see citing works
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 · see citing works
Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · see citing works
Toward optimal feature selection
Koller, D., & Sahami, M. (1996) · Cited by 1,436 · see citing works
Network Dissection: Quantifying Interpretability of Deep Visual Representations
Bau, D., Zhou, B., Khosla, A., Oliva, A., & Torralba, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.354 · Cited by 1,389 · see citing works
On Relevance, Probabilistic Indexing and Information Retrieval
Maron, M. E., & Kuhns, J. L. (1960) · Journal of the ACM · doi:10.1145/321033.321035 · Cited by 908 · see citing works
A Survey of Methods for Explaining Black Box Models
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019) · ACM Computing Surveys · doi:10.1145/3236009 · Cited by 629 · see citing works
Argumentation in Artificial Intelligence
Bench-capon, T., Prakken, H., & Sartor, G. (2009) · Springer eBooks · doi:10.1007/978-0-387-98197-0 · Cited by 573 · see citing works
Goldszmidt, M. (2011) · Wiley Encyclopedia of Operations Research and Management Science · doi:10.1002/9780470400531.eorms0099 · Cited by 351 · see citing works
A Symbolic Approach to Explaining Bayesian Network Classifiers
Shih, A., Choi, A., & Darwiche, A. Y. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/708 · Cited by 208 · see citing works
CXPlain: Causal Explanations for Model Interpretation under UncertaintyPreprint
Schwab, P., & Karlen, W. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12336 · Cited by 73 · see citing works
Compiling Bayesian Network Classifiers into Decision Graphs
Shih, A., Choi, A., & Darwiche, A. Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33017966 · Cited by 58 · see citing works
Same-decision probability: A confidence measure for threshold-based decisions
Choi, A., Xue, Y., & Darwiche, A. Y. (2012) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2012.04.005 · Cited by 29 · see citing works
Explaining Bayesian Networks Using Argumentation
Timmer, S. T., Meyer, J. C., Prakken, H., Renooij, S., & Bart Verheij, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-20807-7_8 · Cited by 28 · see citing works
Explanation Trees For Causal Bayesian Networks
Nielsen, U. H., Pellet, J., & Elisseeff, A. (2008) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.6911 · Cited by 26 · see citing works
Graphical Explanation in Bayesian Networks
Lacave, C., Atienza, R., & Díez, F. J. (2000) · Lecture notes in computer science · doi:10.1007/3-540-39949-6_16 · Cited by 13 · see citing works
Value of Information Based on Decision Robustness
Chen, S., Choi, A., & Darwiche, A. Y. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9684 · Cited by 10 · see citing works
Flagged first, then by citations
Research works printed but not linked: 4
- Bielza and Larrañaga, 2014] Concha Bielza and Pedro Larrañaga. Discrete Bayesian network classifiers: A survey. ACM Computing Surveys, 47(1):5:1-5:43, 2014.
- Lacave and Díez, 2002] Carmen Lacave and Fran- cisco Javier Díez. A review of explanation methods for Bayesian networks. Knowledge Engineering Review, 17(2):107-127, 2002.
- Pearl, 1989] Judea Pearl. Probabilistic reasoning in intel- ligent systems -networks of plausible inference. Morgan Kaufmann series in representation and reasoning. Morgan Kaufmann, 1989.
- Guillermo Ricardo Simari and Iyad Rahwan, editors. Argumentation in Artificial Intel- ligence. Springer, 2009.
Cited by
Sorted by citations
Nauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · ACM Computing Surveys · doi:10.1145/3583558 · Cited by 590 · see citing works
Benchmarking and survey of explanation methods for black box models
Bodria, F., Giannotti, F., Guidotti, R., Naretto, F., Pedreschi, D., & Rinzivillo, S. (2023) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-023-00933-9 · Cited by 353 · see citing works
Ding, W., Abdel‐Basset, M., Hawash, H., & Ali, A. M. A. (2022) · Information Sciences · doi:10.1016/j.ins.2022.10.013 · Cited by 196 · see citing works
Čyras, K., Rago, A., Albini, E., Baroni, P., & Toni, F. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/600 · Cited by 116 · see citing works
Self-citationCounterfactual Shapley Additive Explanations
Albini, E., Long, J., Dervovic, D., & Magazzeni, D. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3533168 · Cited by 74 · see citing works
Self-citationČyras, K., de Oliveira, T. C. R., Karamlou, A., & Toni, F. (2020) · Argument & Computation · doi:10.3233/aac-200523 · Cited by 24 · see citing works
Self-citationFactual and Counterfactual Explanations in Fuzzy Classification Trees
Fernandez, G., Aledo, J., Gamez, J., & Puerta, J. (2022) · IEEE transactions on fuzzy systems · doi:10.1109/tfuzz.2022.3179582 · Cited by 18 · see citing works
Formalising the Robustness of Counterfactual Explanations for Neural Networks
Jiang, J., Leofante, F., Rago, A., & Toni, F. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26740 · Cited by 22 · see citing works
Self-citationIncorporating prior knowledge from counterfactuals into knowledge graph reasoning
Wang, Z., Li, L., Zeng, D. D., & Wu, X. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107035 · Cited by 17 · see citing works
Counterfactual Building and Evaluation via eXplainable Support Vector Data Description
Carlevaro, A., Lenatti, M., Paglialonga, A., & Mongelli, M. (2022) · IEEE Access · doi:10.1109/access.2022.3180026 · Cited by 14 · see citing works
Interpretability for reliable, efficient, and self-cognitive DNNs: From theories to applications
Kang, X., Guo, J., Song, B., Cai, B., Sun, H., & Zhang, Z. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126267 · Cited by 14 · see citing works
Collaboratively weighted naive Bayes
Zhang, H., Jiang, L., & Li, C. (2021) · Knowledge and Information Systems · doi:10.1007/s10115-021-01622-z · Cited by 10 · see citing works
Interval abstractions for robust counterfactual explanations
Jiang, J., Leofante, F., Rago, A., & Toni, F. (2024) · Artificial Intelligence · doi:10.1016/j.artint.2024.104218 · Cited by 9 · see citing works
Self-citationA New Class of Explanations for Classifiers with Non-binary Features
Ji, C., & Darwiche, A. Y. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43619-2_8 · Cited by 8 · see citing works
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 · see citing works
Machine Reasoning ExplainabilityPreprint
Čyras, K., Badrinath, R., Mohalik, S. K., Mujumdar, A. P., Nikou, A., Previti, A., Sundararajan, V., & Feljan, A. V. (2020) · arXiv (Cornell University) · doi:10.4230/lipics.cp.2026.62 · Cited by 11 · see citing works
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 7 · see citing works
Self-citationOn the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
Albini, E., Sharma, S., Mishra, S., Dervovic, D., & Magazzeni, D. (2023) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3600211.3604676 · Cited by 7 · see citing works
Self-citationTowards Explainable Proactive Robot Interactions for Groups of People in Unstructured Environments
Love, T., Andriella, A., & Alenyà, G. (2024) · IEEE/ACM International Conference on Human-Robot Interaction · doi:10.1145/3610978.3640734 · Cited by 9 · see citing works
What-If XAI Framework (WiXAI): From Counterfactuals towards Causal Understanding
Kshetry, N., & Kantardzic, M. M. (2024) · Journal of Computer and Communications · doi:10.4236/jcc.2024.126011 · Cited by 5 · see citing works
Dakhli, R., & Barhoumi, W. (2024) · 2024 IEEE/ACS 21st International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa63423.2024.10912611 · Cited by 5 · see citing works
Fan, Z., Chen, G., Chang, K., Khan, S., & Franco, M. (2024) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero58975.2024.10521144 · Cited by 4 · see citing works
Canha, D., Sylvain Kubler, A., Främling, K., & Fagherazzi, G. (2025) · ACM Computing Surveys · doi:10.1145/3737445 · Cited by 5 · see citing works
CGS-Mask: Making Time Series Predictions Intuitive for All
Lu, F., Li, W., Sun, Y., Song, C., Ren, Y., & Zomaya, A. Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i13.29325 · Cited by 4 · see citing works
Explainable artificial intelligence (XAI) for healthcare decision-making
Zeng, Z. (2022) · doi:10.32657/10356/155849 · Cited by 4 · see citing works
Ali, A., Li, X., Mashwani, W. K., Abiad, M., & Tenruh, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-16825-5 · Cited by 3 · see citing works
Even-if Explanations: Formal Foundations, Priorities and Complexity
Alfano, G., Greco, S., Mandaglio, D., Parisi, F., Shahbazian, R., & Trubitsyna, I. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i15.33684 · Cited by 3 · see citing works
Relative Keys: Putting Feature Explanation into Context
An, S., & Cao, Y. (2024) · Proceedings of the ACM on Management of Data · doi:10.1145/3639263 · Cited by 3 · see citing works
What Would I Do If…? Promoting Understanding in HRI through Real-Time Explanations in the Wild
Love, T., Andriella, A., & Alenyà, G. (2024) · 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN) · doi:10.1109/ro-man60168.2024.10731403 · Cited by 9 · see citing works
Explanation via Machine Arguing
Cocarascu, O., Rago, A., & Toni, F. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60067-9_3 · Cited by 2 · see citing works
Self-citationDinh, D., Nguyen, T.-A., Nguyen, N.-T., Le, N., & Le, B. H. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06945-w · Cited by 1 · see citing works
Perspective Chapter: Validation and Quality Metrics of Machine Learning Explanations
García-Cuesta, E., & González, A. M. L. (2026) · IntechOpen eBooks · doi:10.5772/intechopen.1013468 · Cited by 1 · see citing works
Best of both worlds: contextual feature explanation
An, S., Cao, Y., Li, J., & Li, Y. (2026) · The VLDB Journal · doi:10.1007/s00778-026-00998-0 · Cited by 1 · see citing works
Explaining Causal Models with Argumentation: the Case of Bi-variate Reinforcement
Rago, A., Baroni, P., & Toni, F. (2022) · Principles of Knowledge Representation and Reasoning · doi:10.24963/kr.2022/52 · Cited by 1 · see citing works
Self-citationPandian, A. A., Ramalingam, V., Subramanian, J. V., Kumar, K. P. M., & Padmini, S. (2025) · doi:10.1002/9781394249312.ch18 · Cited by 1 · see citing works
Applying Abstract Argumentation to Normal-Form Games
Cheng, Y., Liao, B., & Luo, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-82017-6_19
CoSP: co-selection pick for a global explainability of black box machine learning models
Mansouri, D. E. K., Benkabou, S.-E., Meddahi, K., Hadjali, A., Mesmoudi, A., Benabdeslem, K., & Chaib, S. (2023) · World Wide Web · doi:10.1007/s11280-023-01213-8
Towards Personalized Anti-Phishing: Counterfactual Explanation ApproachPreprint
Fan, Z., Li, W., Laskey, K. B., & Chang, K. (2024) · Research Square · doi:10.21203/rs.3.rs-4335902/v1
Advanced Methods for Enhancing the Interpretability of AI tools in the Energy Sector
Parginos, K. (2025) · theses.fr (ABES) · doi:10.70675/eb35a92dz272dz4108z9978za36e7cefd388
- Authors
- Albini, E., Rago, A., Baroni, P., & Toni, F.
- Affiliations
- Imperial College London (GB)
- University of Brescia (IT)
- Venue
- Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
- Published
- 2020-07
- Pages
- 451-457
- OpenAlex
- W3035666228
- Cited by
- 39
- References
- 19
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 9 · 2023: 7 · 2022: 6 · 2021: 6 · 2020: 3
- FWCI
- 2.10
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- Institutional Research Information System (Università degli Studi di Brescia) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Keywords
- counterfactual explanations, Bayesian network classifiers, explainable AI, multi-label classification, multidimensional 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
