Skip to main content
SpringerLink
Log in
Book cover

Reasoning Web. Causality, Explanations and Declarative Knowledge pp 1–23Cite as

Attribution-Scores and Causal Counterfactuals as Explanations in Artificial Intelligence

  • Chapter
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13759))

Abstract

In this expository article we highlight the relevance of explanations for artificial intelligence, in general, and for the newer developments in explainable AI, referring to origins and connections of and among different approaches. We describe in simple terms, explanations in data management and machine learning that are based on attribution-scores, and counterfactuals as found in the area of causality. We elaborate on the importance of logical reasoning when dealing with counterfactuals, and their use for score computation.

L. Bertossi—Member of the Millennium Institute for Foundations of Data Research (IMFD, Chile).

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   49.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   64.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Notes

  1. 1.

    If some other non-classical logic is used instead, \(\models \) has to be replaced by the corresponding entailment criterion [23].

  2. 2.

    Example 7 will show an actual cause that is not a counterfactual cause.

  3. 3.

    Less “trivial” cases will be shown in Example 7.

  4. 4.

    We are assuming that classifiers are binary, i.e. they return labels 0 or 1. For simplicity and uniformity, but without loss of generality, we will assume that label 1 is the one we want to explain.

  5. 5.

    Another \(\#P\)-complete problem is \(\#{ Hamiltonian}\), about counting the number of Hamiltonian cycles in a graph. Its decision version, about the existence of a Hamiltonian cycle, is \({ NP}\)-complete.

  6. 6.

    Interestingly, the decision version of the problem, i.e. of deciding if a formula in \({ Monotone}2{ CNF}\) is satisfiable, is trivially tractable: the assignment that makes all atoms true satisfies the formula.

  7. 7.

    It could be transformed into a dDBC, but this would make the circuit grow. The transformation cost is always a concern in the area of knowledge compilation. For some classes of BCs, a transformation into another class could take exponential time; sometimes exponential on a fixed parameter, etc. [1, 26].

  8. 8.

    It is worth mentioning that ASP and DLV have been used to specify and compute model-based diagnoses, both in their abductive and consistency-based formulations [25].

References

  1. Antoine Amarilli, A., Capelli, F., Monet, M., Senellart, P.: Connecting knowledge compilation classes width parameters. Theory Comput. Syst. 64, 861–914 (2020)

    Article  MathSciNet  MATH  Google Scholar 

  2. Arenas, M., Barcelo, P., Bertossi, L., Monet, M.: The tractability of SHAP-scores over deterministic and decomposable boolean circuits. In: Proceedings of AAAI (2021)

    Google Scholar 

  3. Arenas, M., Barcelo, P., Bertossi, L., Monet, M.: The tractability of SHAP-scores over deterministic and decomposable boolean circuits. Extended version of AAAI 2021 paper. arXiv:2104.08015 (2021)

  4. Arenas, M., Pablo Barcelo, P., Romero, M., Subercaseaux, B.: On computing probabilistic explanations for decision trees. In: Proceedings of NeurIPS (2022)

    Google Scholar 

  5. Baral, C., Gelfond, M., Rushton, N.: Probabilistic reasoning with answer sets. Theory Pract. Logic Program. 9(1), 57–144 (2009)

    Article  MathSciNet  MATH  Google Scholar 

  6. Bertossi, L., Salimi, B.: From causes for database queries to repairs and model-based diagnosis and back. Theory Comput. Syst. 61(1), 191–232 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  7. Bertossi, L., Salimi, B.: Causes for query answers from databases: datalog abduction, view-updates, and integrity constraints. Int. J. Approximate Reasoning 90, 226–252 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  8. Bertossi, L., Li, J., Schleich, M., Suciu, D., Vagena, Z.: Causality-based explanation of classification outcomes. In: Proceedings of 4th International Workshop on “Data Management for End-to-End Machine Learning” (DEEM) at ACM SIGMOD/PODS, pp. 6:1–6:10 (2020)

    Google Scholar 

  9. Bertossi, L.: Specifying and computing causes for query answers in databases via database repairs and repair programs. Knowl. Inf. Syst. 63(1), 199–231 (2021)

    Article  Google Scholar 

  10. Bertossi, L.: Score-based explanations in data management and machine learning: an answer-set programming approach to counterfactual analysis. In: Šimkus, M., Varzinczak, I. (eds.) Reasoning Web 2021. LNCS, vol. 13100, pp. 145–184. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-95481-9_7

    Chapter  Google Scholar 

  11. Bertossi, L., Reyes, G.: Answer-set programs for reasoning about counterfactual interventions and responsibility scores for classification. In: Katzouris, N., Artikis, A. (eds.) ILP 2021. LNCS, vol. 13191, pp. 41–56. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-97454-1_4

    Chapter  Google Scholar 

  12. Bertossi, L.: Declarative approaches to counterfactual explanations for classification. Theory Pract. Log. Program. (2020). https://doi.org/10.1017/S1471068421000582, arXiv:2011.07423

  13. Brewka, G., Eiter, T., Truszczynski, M.: Answer set programming at a glance. Commun. ACM 54(12), 92–103 (2011)

    Article  Google Scholar 

  14. Bryant, R.E.: Graph-based algorithms for boolean function manipulation. IEEE Tran. Comput. C-35, 677–691 (1986)

    Google Scholar 

  15. Burkart, N., Huber, M.F.: A survey on the explainability of supervised machine learning. J. Artif. Intell. Res. 70, 245–317 (2021)

    Article  MathSciNet  MATH  Google Scholar 

  16. Chatila, R., et al.: Trustworthy AI. In: Braunschweig, B., Ghallab, M. (eds.) Reflections on Artificial Intelligence for Humanity. LNCS (LNAI), vol. 12600, pp. 13–39. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-69128-8_2

    Chapter  Google Scholar 

  17. Chen, C., Lin, K., Rudin, C., Shaposhnik, Y., Wang, S., Wang, T.: An interpretable model with globally consistent explanations for credit risk. arXiv:1811.12615 (2018)

  18. Chockler, H., Halpern, J.Y.: Responsibility and blame: a structural-model approach. J. Artif. Intell. Res. 22, 93–115 (2004)

    Article  MathSciNet  MATH  Google Scholar 

  19. Darwiche, A., Marquis, P.: A knowledge compilation map. J. Artif. Intell. Res. 17, 229–264 (2002)

    Article  MathSciNet  MATH  Google Scholar 

  20. Darwiche, A.: On the tractable counting of theory models and its application to truth maintenance and belief revision. J. Appl. Non-Classical Log. 11(1–2), 11–34 (2011)

    MathSciNet  MATH  Google Scholar 

  21. de Kleer, J., Mackworth, A., Reiter, R.: Characterizing diagnoses and systems. Artif. Intell. 56(2–3), 197–222 (1992)

    Article  MathSciNet  MATH  Google Scholar 

  22. Eiter, T., Gottlob, G.: On the complexity of propositional knowledge base revision, updates, and counterfactuals. Artif. Intell. 57(2–3), 227–270 (1992)

    Article  MathSciNet  MATH  Google Scholar 

  23. Eiter, T., Gottlob, G.: The complexity of logic-based abduction. J. ACM 42(1), 3–42 (1995)

    Article  MathSciNet  MATH  Google Scholar 

  24. Eiter, T., Gottlob, G., Leone, N.: Abduction from logic programs: semantics and complexity. Theor. Comput. Sci. 189(1–2), 129–177 (1997)

    Article  MathSciNet  MATH  Google Scholar 

  25. Eiter, T., Faber, W., Leone, N., Pfeifer, G.: The diagnosis frontend of the DLV system. AI Communun. 12(1–2), 99–111 (1999). Extended version as Tech. Report DBAI-TR-98-20, TU Vienna, 1998

    Google Scholar 

  26. Ferrara, A., Pan, G., Vardi, M.Y.: Treewidth in verification: local vs. global. In: Sutcliffe, G., Voronkov, A. (eds.) LPAR 2005. LNCS (LNAI), vol. 3835, pp. 489–503. Springer, Heidelberg (2005). https://doi.org/10.1007/11591191_34

    Chapter  Google Scholar 

  27. Gomes, C.P., Sabharwal, A., Selman, B.: Model counting. In: Handbook of Satisfiability, pp. 993–1014. IOS Press (2009)

    Google Scholar 

  28. Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 1–93 (2018)

    Article  Google Scholar 

  29. Halpern, J., Pearl, J.: Causes and explanations: a structural-model approach. Part I: causes. Br. J. Philos. Sci. 56(4), 843–887 (2005)

    Article  MATH  Google Scholar 

  30. Halpern, J.: Actual Causality. MIT Press, Cambridge (2016)

    Book  MATH  Google Scholar 

  31. Hahn, S., Janhunen, T., Kaminski, R., Romero, J., Rühling, N., Schaub, T.: Plingo: a system for probabilistic reasoning in Clingo based on LP MLN. In: Proceedings of RuleML+RR, pp. 54–62 (2022)

    Google Scholar 

  32. Hunter, A., Konieczny, S.: On the measure of conflicts: shapley inconsistency values. Artif. Intell. 174(14), 1007–1026 (2010)

    Article  MathSciNet  MATH  Google Scholar 

  33. Huang, X., Izza, Y., Ignatiev, A., Cooper, M.C., Asher, N., Marques-Silva, J.: Tractable explanations for d-DNNF classifiers. In: Proceedings of AAAI, pp. 5719–5728 (2022)

    Google Scholar 

  34. Ignatiev, A., Narodytska, N., Marques-Silva, J.: Abduction-based explanations for machine learning models. In: Proceedings of AAAI, pp. 1511–1519 (2019)

    Google Scholar 

  35. Karimi, A.-H., von Kügelgen, B.J., Schölkopf, B., Valera, I.: Algorithmic recourse under imperfect causal knowledge: a probabilistic approach. In: Proceedings of NeurIPS (2020)

    Google Scholar 

  36. Karimi, A.-H., Barthe, G., Schölkopf, B., Valera, I.: A survey of algorithmic recourse: contrastive explanations and consequential recommendations. ACM Comput. Surv. 55(5), 95:1–95:29 (2023)

    Google Scholar 

  37. Lee, J., Yang, Z.: LPMLN, weak constraints, and P-log. In: Proceedings of AAAI, pp. 1170–1177 (2017)

    Google Scholar 

  38. Lee, J., Yang, Z.: Statistical relational extension of answer set programming. In: Bertossi, L., Xiao, G. (eds.) Reasoning Web. Causality, Explanations and Declarative Knowledge. LNCS, vol. 13759, pp. 132–160. Springer, Cham (2023)

    Google Scholar 

  39. Leone, N., et al.: The DLV system for knowledge representation and reasoning. ACM Trans. Comput. Log. 7(3), 499–562 (2006)

    Google Scholar 

  40. Livshits, E., Bertossi, L., Kimelfeld, B., Sebag, M.: Query games in databases. ACM SIGMOD Rec. 50(1), 78–85 (2021)

    Article  MATH  Google Scholar 

  41. Livshits, E., Bertossi, L., Kimelfeld, B., Sebag, M.: The shapley value of tuples in query answering. Log. Methods Comput. Sci. 17(3), 22:1–22:33 (2021)

    Google Scholar 

  42. Livshits, E., Kimelfeld, E.: The shapley value of inconsistency measures for functional dependencies. Log. Methods Comput. Sci. 18(2), 20:1–20:33 (2022)

    Google Scholar 

  43. Lundberg, S., Lee, S.-I.: A unified approach to interpreting model predictions. In: Proceedings of NIPS, pp. 4765–4774 (2017)

    Google Scholar 

  44. Lundberg, S.M., Erion, G., Chen, H., DeGrave, A., Prutkin, J., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., Lee, S.-I.: From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2(1), 56–67 (2020)

    Article  Google Scholar 

  45. Marques-Silva, J.: Logic-based explainability in machine learning. In: Bertossi, L., Xiao, G. (eds.) Reasoning Web. Causality, Explanations and Declarative Knowledge. LNCS, vol. 13759, pp. 24–104. Springer, Cham (2023)

    Google Scholar 

  46. Marquis, P.: Extending abduction from propositional to first-order logic. In: Jorrand, P., Kelemen, J. (eds.) FAIR 1991. LNCS, vol. 535, pp. 141–155. Springer, Heidelberg (1991). https://doi.org/10.1007/3-540-54507-7_12

    Chapter  Google Scholar 

  47. Meliou, A., Gatterbauer, W., Moore, K.F., Suciu, D.: The complexity of causality and responsibility for query answers and non-answers. In: Proceedings of VLDB, pp. 34–41 (2010)

    Google Scholar 

  48. Meliou, A., Gatterbauer, W., Halpern, J.Y., Koch, C., Moore, K.F., Suciu, D.: Causality in databases. IEEE Data Eng. Bull. 33(3), 59–67 (2010)

    Google Scholar 

  49. Miller, T.: Contrastive explanation: a structural-model approach. Knowl. Eng. Rev. 36(4), 1–24 (2021)

    Google Scholar 

  50. Minh, D., Xiang-Wang, H., Fen-Li, Y., Nguyen, T.N.: Explainable artificial intelligence: a comprehensive review. Artif. Intell. Rev. 55, 3503–3568 (2022)

    Article  Google Scholar 

  51. Molnar, C.: Interpretable machine learning: a guide for making black box models explainable, (2020). https://christophm.github.io/interpretable-ml-book

  52. Papadimitriou, P.: Computational Complexity. Addison-Wesley (1994)

    Google Scholar 

  53. Pearl, J.: Causality: Models, Reasoning and Inference, 2nd edn. Cambridge University Press, Cambridge (2009)

    Book  MATH  Google Scholar 

  54. Peirce, C.S.: Collected papers of Charles Sanders Peirce. In: Hartsthorne, C., Weiss, P. (eds.) vol. 2. Harvard University Press (1931)

    Google Scholar 

  55. Poole, D., Mackworth, A.K.: Artificial Intelligence. Section 5.7, 2nd edn. Cambridge University Press (2017)

    Google Scholar 

  56. Reiter, R.: A theory of diagnosis from first principles. Artif. Intell. 32(1), 57–95 (1987)

    Article  MathSciNet  MATH  Google Scholar 

  57. Roth, A.E.: The Shapley Value: Essays in Honor of Lloyd S. Shapley. Cambridge University Press, Cambridge (1988)

    Book  MATH  Google Scholar 

  58. Roy, S., Salimi, B.: Causal inference in data analysis with applications to fairness and explanations. In: Bertossi, L., Xiao, G. (eds.) Reasoning Web. Causality, Explanations and Declarative Knowledge. LNCS, vol. 13759, pp. 105–131. Springer, Cham (2023)

    Google Scholar 

  59. Shapley, L.S.: A value for n-person games. Contrib. Theory Games 2(28), 307–317 (1953)

    MathSciNet  MATH  Google Scholar 

  60. Shi, W., Shih, A., Darwiche, A., Choi, A.: On tractable representations of binary neural networks. In: Proceedings of KR, pp. 882–892 (2020)

    Google Scholar 

  61. Struss, P.: Model-based problem solving. In: Handbook of Knowledge Representation, chap. 4, pp. 395–465. Elsevier (2008)

    Google Scholar 

  62. Ustun, B., Spangher, A., Liu, Y.: Actionable recourse in linear classification. In: Proceedings of FAT, pp. 10–19 (2019)

    Google Scholar 

  63. Valiant, L.G.: The complexity of enumeration and reliability problems. SIAM J. Comput. 8(3), 410–421 (1979)

    Article  MathSciNet  MATH  Google Scholar 

  64. Van den Broeck, G., Lykov, A., Schleich, M., Suciu, D.: On the tractability of shap explanations. In: Proceedings of AAAI, pp. 6505–6513 (2021)

    Google Scholar 

  65. Verma, S., et al.: Counterfactual explanations and algorithmic recourses for machine learning: a review. arXiv:2010.10596 (2022)

Download references

Acknowledgements

Part of this work was funded by ANID - Millennium Science Initiative Program - Code ICN17002. The author is a Professor Emeritus at Carleton University, Ottawa, Canada; and a Senior Universidad Adolfo Ibáñez (UAI) Fellow, Chile. Comments by Paloma Bertossi on an earlier version of the article are much appreciated.

Author information

Authors and Affiliations

  1. SKEMA Business School, Montreal, Canada

    Leopoldo Bertossi

Authors
  1. Leopoldo Bertossi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Leopoldo Bertossi .

Editor information

Editors and Affiliations

  1. SKEMA Business School, Montreal, Canada

    Leopoldo Bertossi

  2. University of Bergen, Bergen, Norway

    Guohui Xiao

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Bertossi, L. (2023). Attribution-Scores and Causal Counterfactuals as Explanations in Artificial Intelligence. In: Bertossi, L., Xiao, G. (eds) Reasoning Web. Causality, Explanations and Declarative Knowledge. Lecture Notes in Computer Science, vol 13759. Springer, Cham. https://doi.org/10.1007/978-3-031-31414-8_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-31414-8_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-31413-1

  • Online ISBN: 978-3-031-31414-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation