{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T18:25:46Z","timestamp":1758479146120,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031503955"},{"type":"electronic","value":"9783031503962"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,21]],"date-time":"2024-01-21T00:00:00Z","timestamp":1705795200000},"content-version":"vor","delay-in-days":20,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>One of the most widely adopted approaches for eXplainable Artificial Intelligence (XAI) involves employing of Shapley values (SVs) to determine the relative importance of input features. While based on a solid mathematical foundation derived from cooperative game theory, SVs have a significant drawback: high computational cost. Calculating the exact SV is an NP-hard problem, necessitating the use of approximations, particularly when dealing with more than twenty features. On the other hand, determining SVs for all features is seldom necessary in practice; users are primarily interested in the most important ones only. This paper introduces the Economic Hierarchical Shapley values (ecoShap) method for calculating SVs for the most crucial features only, with reduced computational cost. EcoShap iteratively expands disjoint groups of features in a tree-like manner, avoiding the expensive computations for the majority of less important features. Our experimental results across eight datasets demonstrate that the proposed technique efficiently identifies top features; at a 50% reduction in computational costs, it can determine between three and seven of the most important features.<\/jats:p>","DOI":"10.1007\/978-3-031-50396-2_2","type":"book-chapter","created":{"date-parts":[[2024,1,20]],"date-time":"2024-01-20T14:02:08Z","timestamp":1705759328000},"page":"24-42","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["EcoShap: Save Computations by\u00a0only\u00a0Calculating Shapley Values for\u00a0Relevant Features"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7055-2706","authenticated-orcid":false,"given":"Parisa","family":"Jamshidi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7796-5201","authenticated-orcid":false,"given":"S\u0142awomir","family":"Nowaczyk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2590-6661","authenticated-orcid":false,"given":"Mahmoud","family":"Rahat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,21]]},"reference":[{"key":"2_CR1","unstructured":"Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017)"},{"issue":"3","key":"2_CR2","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/3236386.3241340","volume":"16","author":"ZC Lipton","year":"2018","unstructured":"Lipton, Z.C.: The mythos of model interpretability: in machine learning, the concept of interpretability is both important and slippery. Queue 16(3), 31\u201357 (2018)","journal-title":"Queue"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201c why should I trust you?\u201d explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135\u20131144 (2016)","DOI":"10.1145\/2939672.2939778"},{"issue":"10","key":"2_CR4","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2347736.2347755","volume":"55","author":"P Domingos","year":"2012","unstructured":"Domingos, P.: A few useful things to know about machine learning. Commun. ACM 55(10), 78\u201387 (2012)","journal-title":"Commun. ACM"},{"key":"2_CR5","unstructured":"Kusner, M.J., Loftus, J., Russell, C., Silva, R.: Counterfactual fairness. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1007\/978-3-030-86520-7_40","volume-title":"Machine Learning and Knowledge Discovery in Databases. Research Track","author":"A Van Looveren","year":"2021","unstructured":"Van Looveren, A., Klaise, J.: Interpretable counterfactual explanations guided by prototypes. In: Oliver, N., P\u00e9rez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds.) ECML PKDD 2021. LNCS (LNAI), vol. 12976, pp. 650\u2013665. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86520-7_40"},{"key":"2_CR7","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Model-agnostic interpretability of machine learning. arXiv preprint arXiv:1606.05386 (2016)"},{"key":"2_CR8","unstructured":"Sundararajan, M., Najmi, A.: The many shapley values for model explanation. In: International Conference on Machine Learning, pp. 9269\u20139278. PMLR (2020)"},{"key":"2_CR9","unstructured":"Karla\u0161, B., et al.: Data debugging with shapley importance over end-to-end machine learning pipelines. arXiv preprint arXiv:2204.11131 (2022)"},{"key":"2_CR10","unstructured":"Shapley, L.S., et al.: A Value for N-person Games: Princeton University Press, Princeton (1953)"},{"key":"2_CR11","unstructured":"Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR12","unstructured":"Sundararajan, M., Dhamdhere, K., Agarwal, A.: The shapley taylor interaction index. In: International Conference on Machine Learning, pp. 9259\u20139268. PMLR (2020)"},{"key":"2_CR13","unstructured":"Harris, C., Pymar, R., Rowat, C.: Joint shapley values: a measure of joint feature importance. arXiv preprint arXiv:2107.11357 (2021)"},{"key":"2_CR14","unstructured":"Shapley, L.S.: \u201cNotes on the n-person game \u2013 ii: the value of an n-person game,\u201d RAND Corporation, Santa Monica, Calif., Technical Report (1951)"},{"key":"2_CR15","unstructured":"Ancona, M., Oztireli, C., Gross, M.: Explaining deep neural networks with a polynomial time algorithm for shapley value approximation. In: International Conference on Machine Learning, pp. 272\u2013281. PMLR (2019)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Rozemberczki, B., et al.: The shapley value in machine learning. arXiv preprint arXiv:2202.05594 (2022)","DOI":"10.24963\/ijcai.2022\/778"},{"key":"2_CR17","unstructured":"Wang, G.: Interpret federated learning with shapley values. arXiv preprint arXiv:1905.04519 (2019)"},{"key":"2_CR18","unstructured":"Dua, D., Graff, C.: UCI machine learning repository (2017). http:\/\/archive.ics.uci.edu\/ml"},{"key":"2_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1007\/978-3-319-23485-4_53","volume-title":"Progress in Artificial Intelligence","author":"K Fernandes","year":"2015","unstructured":"Fernandes, K., Vinagre, P., Cortez, P.: A proactive intelligent decision support system for predicting the popularity of online news. In: Pereira, F., Machado, P., Costa, E., Cardoso, A. (eds.) EPIA 2015. LNCS (LNAI), vol. 9273, pp. 535\u2013546. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-23485-4_53"},{"key":"2_CR20","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.commatsci.2018.07.052","volume":"154","author":"K Hamidieh","year":"2018","unstructured":"Hamidieh, K.: A data-driven statistical model for predicting the critical temperature of a superconductor. Comput. Mater. Sci. 154, 346\u2013354 (2018)","journal-title":"Comput. Mater. Sci."},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785\u2013794 (2016)","DOI":"10.1145\/2939672.2939785"},{"key":"2_CR22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63, 3\u201342 (2006)","journal-title":"Mach. Learn."}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence. ECAI 2023 International Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-50396-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,20]],"date-time":"2024-01-20T14:09:36Z","timestamp":1705759776000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-50396-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031503955","9783031503962"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-50396-2_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"21 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Krak\u00f3w","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","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":"30 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecai2023.eu\/","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 and SMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"134","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":"69","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":"51% - 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":"2.86","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":"2.15","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)"}},{"value":"Presented figures are relevant for the ECAI 2023 workshops","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}