{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T05:28:21Z","timestamp":1754112501886,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031408366"},{"type":"electronic","value":"9783031408373"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T00:00:00Z","timestamp":1692662400000},"content-version":"vor","delay-in-days":233,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Asymmetric Shapley values (ASVs) are an extension of Shapley values that allow a user to incorporate partial causal knowledge into the explanation process. Unfortunately, computing ASVs requires sampling permutations, which quickly becomes computationally expensive. We propose A-PDD-SHAP, an algorithm that employs a functional decomposition approach to approximate ASVs at a speed orders of magnitude faster compared to permutation sampling, which significantly reduces the amortized complexity of computing ASVs when many explanations are needed. Apart from this, once the A-PDD-SHAP model is trained, it can be used to compute both symmetric and asymmetric Shapley values without having to re-train or re-sample, allowing for very efficient comparisons between different types of explanations.<\/jats:p>","DOI":"10.1007\/978-3-031-40837-3_2","type":"book-chapter","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T23:02:25Z","timestamp":1692658945000},"page":"13-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Approximation of\u00a0Asymmetric Shapley Values Using Functional Decomposition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4130-8151","authenticated-orcid":false,"given":"Arne","family":"Gevaert","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1085-8428","authenticated-orcid":false,"given":"Anna","family":"Saranti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6786-5194","authenticated-orcid":false,"given":"Andreas","family":"Holzinger","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0415-1506","authenticated-orcid":false,"given":"Yvan","family":"Saeys","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,22]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103502","volume":"298","author":"K Aas","year":"2021","unstructured":"Aas, K., Jullum, M., L\u00f8land, A.: Explaining individual predictions when features are dependent: more accurate approximations to Shapley values. Artif. Intell. 298, 103502 (2021). https:\/\/doi.org\/10.1016\/j.artint.2021.103502","journal-title":"Artif. Intell."},{"key":"2_CR2","unstructured":"Chen, H., Janizek, J.D., Lundberg, S., Lee, S.I.: True to the model or true to the data? (2020)"},{"issue":"5","key":"2_CR3","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29(5), 1189\u20131232 (2001)","journal-title":"Ann. Stat."},{"key":"2_CR4","unstructured":"Frye, C., de Mijolla, D., Begley, T., Cowton, L., Stanley, M., Feige, I.: Shapley explainability on the data manifold. In: International Conference on Learning Representations. arXiv (2021)"},{"key":"2_CR5","unstructured":"Frye, C., Rowat, C., Feige, I.: Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1229\u20131239. Curran Associates, Inc. (2020)"},{"key":"2_CR6","unstructured":"Gevaert, A., Saeys, Y.: PDD-SHAP: fast approximations for Shapley values using functional decomposition. In: Workshop on Trustworthy Artificial Intelligence as a Part of the ECML\/PKDD 22 Program (2022)"},{"issue":"3","key":"2_CR7","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s40708-016-0038-2","volume":"3","author":"D Girardi","year":"2016","unstructured":"Girardi, D., et al.: Interactive knowledge discovery with the doctor-in-the-loop: a practical example of cerebral aneurysms research. Brain Inform. 3(3), 133\u2013143 (2016). https:\/\/doi.org\/10.1007\/s40708-016-0038-2","journal-title":"Brain Inform."},{"key":"2_CR8","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/978-3-030-93736-2_33","volume-title":"Machine Learning and Principles and Practice of Knowledge Discovery in Databases","author":"A Holzinger","year":"2021","unstructured":"Holzinger, A.: The next frontier: AI we can really trust. In: Kamp, M., et al. (eds.) ECML PKDD 2021. CCIS, vol. 1524, pp. 427\u2013440. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-93736-2_33"},{"issue":"3","key":"2_CR9","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.inffus.2021.10.007","volume":"79","author":"A Holzinger","year":"2022","unstructured":"Holzinger, A., et al.: Information fusion as an integrative cross-cutting enabler to achieve robust, explainable, and trustworthy medical artificial intelligence. Inf. Fusion 79(3), 263\u2013278 (2022). https:\/\/doi.org\/10.1016\/j.inffus.2021.10.007","journal-title":"Inf. Fusion"},{"issue":"10","key":"2_CR10","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/MC.2021.3092610","volume":"54","author":"A Holzinger","year":"2021","unstructured":"Holzinger, A., M\u00fcller, H.: Toward human\u2013AI interfaces to support explainability and causability in medical AI. Computer 54(10), 78\u201386 (2021). https:\/\/doi.org\/10.1109\/MC.2021.3092610","journal-title":"Computer"},{"key":"2_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/978-3-031-04083-2_2","volume-title":"xxAI - Beyond Explainable AI","author":"A Holzinger","year":"2022","unstructured":"Holzinger, A., Saranti, A., Molnar, C., Biececk, P., Samek, W.: Explainable AI methods - a brief overview. In: Holzinger, A., Goebel, R., Fong, R., Moon, T., M\u00fcller, K.R., Samek, W. (eds.) xxAI 2020. LNAI, vol. 13200, pp. 13\u201338. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-04083-2_2"},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"Hooker, G.: Discovering additive structure in black box functions. In: Proceedings of the 2004 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD 2004, Seattle, WA, USA, p. 575. ACM Press (2004). https:\/\/doi.org\/10.1145\/1014052.1014122","DOI":"10.1145\/1014052.1014122"},{"key":"2_CR13","unstructured":"Kilbertus, N., Rojas Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., Sch\u00f6lkopf, B.: Avoiding discrimination through causal reasoning. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)"},{"key":"2_CR14","volume-title":"Probabilistic Graphical Models: Principles and Techniques","author":"D Koller","year":"2009","unstructured":"Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)"},{"issue":"1","key":"2_CR15","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1038\/s41467-019-08987-4","volume":"10","author":"S Lapuschkin","year":"2019","unstructured":"Lapuschkin, S., W\u00e4ldchen, S., Binder, A., Montavon, G., Samek, W., M\u00fcller, K.R.: Unmasking Clever Hans predictors and assessing what machines really learn. Nat. Commun. 10(1), 1096 (2019)","journal-title":"Nat. Commun."},{"key":"2_CR16","unstructured":"Lundberg, S., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30, pp. 4766\u20134775 (2017)"},{"key":"2_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1\u201338 (2019)","journal-title":"Artif. Intell."},{"key":"2_CR18","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality","author":"J Pearl","year":"2009","unstructured":"Pearl, J.: Causality. Cambridge University Press, Cambridge (2009)"},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Pearl, J., Bareinboim, E.: Transportability of causal and statistical relations: a formal approach. In: 11th International IEEE Conference on Data Mining Workshops, pp. 540\u2013547. IEEE (2011). https:\/\/doi.org\/10.1109\/ICDMW.2011.169","DOI":"10.1109\/ICDMW.2011.169"},{"issue":"4","key":"2_CR20","doi-asserted-by":"publisher","first-page":"924","DOI":"10.3390\/make4040047","volume":"4","author":"A Saranti","year":"2022","unstructured":"Saranti, A., et al.: Actionable explainable AI (AxAI): a practical example with aggregation functions for adaptive classification and textual explanations for interpretable machine learning. Mach. Learn. Knowl. Extract. 4(4), 924\u2013953 (2022). https:\/\/doi.org\/10.3390\/make4040047","journal-title":"Mach. Learn. Knowl. Extract."},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Shapley, L.S.: A value for n-person games. In: Contributions to the Theory of Games, vol. 2, no. 28, pp. 307\u2013317 (1953)","DOI":"10.1515\/9781400881970-018"},{"key":"2_CR22","unstructured":"Sundararajan, M., Najmi, A.: The many Shapley values for model explanation. In: Proceedings of the 37th International Conference on Machine Learning, vol. 119, pp. 9269\u20139278 (2020)"},{"issue":"2","key":"2_CR23","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/2641190.2641198","volume":"15","author":"J Vanschoren","year":"2013","unstructured":"Vanschoren, J., van Rijn, J.N., Bischl, B., Torgo, L.: OpenML: networked science in machine learning. SIGKDD Explor. 15(2), 49\u201360 (2013). https:\/\/doi.org\/10.1145\/2641190.2641198","journal-title":"SIGKDD Explor."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40837-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:32:51Z","timestamp":1710333171000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40837-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031408366","9783031408373"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40837-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CD-MAKE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Cross-Domain Conference for Machine Learning and Knowledge Extraction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Benevento","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cd-make2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cd-make.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"60% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}