{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T10:34:40Z","timestamp":1760524480583,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031300462"},{"type":"electronic","value":"9783031300479"}],"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":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":90,"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>Local surrogate learning is a popular and successful method for machine learning explanation. It uses synthetic transfer data to approximate a complex reference model. The sampling technique used for this transfer data has a significant impact on the provided explanation, but remains relatively unexplored in literature. In this work, we explore alternative sampling techniques in pursuit of more faithful and robust explanations, and present LEMON: a sampling technique that samples directly from the desired distribution instead of reweighting samples as done in other explanation techniques (e.g., LIME). Next, we evaluate our technique in a synthetic and UCI dataset-based experiment, and show that our sampling technique yields more faithful explanations compared to current state-of-the-art explainers.<\/jats:p>","DOI":"10.1007\/978-3-031-30047-9_7","type":"book-chapter","created":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T09:06:06Z","timestamp":1680253566000},"page":"77-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["LEMON: Alternative Sampling for\u00a0More Faithful Explanation Through Local Surrogate Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7612-9319","authenticated-orcid":false,"given":"Dennis","family":"Collaris","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8087-5661","authenticated-orcid":false,"given":"Pratik","family":"Gajane","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1669-9253","authenticated-orcid":false,"given":"Joost","family":"Jorritsma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5128-976X","authenticated-orcid":false,"given":"Jarke J.","family":"van Wijk","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4955-0743","authenticated-orcid":false,"given":"Mykola","family":"Pechenizkiy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,1]]},"reference":[{"key":"7_CR1","series-title":"Human\u2013Computer Interaction Series","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-90403-0_2","volume-title":"Human and Machine Learning","author":"B Abdollahi","year":"2018","unstructured":"Abdollahi, B., Nasraoui, O.: Transparency in fair machine learning: the case of explainable recommender systems. In: Zhou, J., Chen, F. (eds.) Human and Machine Learning. HIS, pp. 21\u201335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-90403-0_2"},{"key":"7_CR2","unstructured":"Alvarez-Melis, D., Jaakkola, T.S.: On the robustness of interpretability methods. In: Workshop Human Interp. Mach. Learn., pp. 66\u201371 (2018)"},{"key":"7_CR3","unstructured":"Ba, J., Caruana, R.: Do deep nets really need to be deep? In: Adv. Neural Inf. Proc. Sys., pp. 2654\u20132662 (2014)"},{"key":"7_CR4","first-page":"1803","volume":"11","author":"D Baehrens","year":"2010","unstructured":"Baehrens, D., Schroeter, T., Harmeling, S., Kawanabe, M., Hansen, K., M\u00fcller, K.R.: How to explain individual classification decisions. J. Mach. Learn. Res. 11, 1803\u20131831 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Barocas, S., Selbst, A.D.: Big data\u2019s disparate impact. California Law Rev. 671\u2013732 (2016)","DOI":"10.2139\/ssrn.2477899"},{"key":"7_CR6","unstructured":"Bastani, O., Kim, C., Bastani, H.: Interpreting blackbox models via model extraction. arXiv preprint arXiv:1705.08504 (2017)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Bucilu\u0103, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Int. Conf. Knowl. Discovery Data Mining, pp. 535\u2013541. ACM SIGKDD (2006)","DOI":"10.1145\/1150402.1150464"},{"key":"7_CR8","unstructured":"Buolamwini, J., Gebru, T.: Gender shades: intersectional accuracy disparities in commercial gender classification. In: Conf. Fairness, Accountability and Transparency, pp. 77\u201391. PMLR (2018)"},{"key":"7_CR9","first-page":"1","volume":"89","author":"DK Citron","year":"2014","unstructured":"Citron, D.K., Pasquale, F.D.: The scored society: due process for automated predictions. Wash. L. Rev. 89, 1 (2014)","journal-title":"Wash. L. Rev."},{"key":"7_CR10","unstructured":"Craven, M., Shavlik, J.W.: Extracting tree-structured representations of trained networks. In: Adv. Neural Inf. Process. Sys., pp. 24\u201330 (1996)"},{"key":"7_CR11","unstructured":"Domingos, P.: Knowledge acquisition from examples via multiple models. In: Int. Conf. Machine Learn., pp. 98\u2013106 (1997)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Edelman, B.G., Luca, M.: Digital discrimination: the case of airbnb.com (2014)","DOI":"10.2139\/ssrn.2377353"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Efron, B., Hastie, T., Johnstone, I., Tibshirani, R.: Least angle regression (2004)","DOI":"10.1214\/009053604000000067"},{"key":"7_CR14","doi-asserted-by":"publisher","unstructured":"Fishman, G.: Monte Carlo: Concepts, Algorithms, and Applications. Springer, New York (2013). https:\/\/doi.org\/10.1007\/978-1-4757-2553-7","DOI":"10.1007\/978-1-4757-2553-7"},{"key":"7_CR15","unstructured":"Garreau, D., Luxburg, U.: Explaining the explainer: a first theoretical analysis of lime. In: Int. Conf. AI Stat., pp. 1287\u20131296. PMLR (2020)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Gass, S.I., Fu, M.C. (eds.): Inverse transform method, p. 815. Springer (2013)","DOI":"10.1007\/978-1-4419-1153-7_200343"},{"issue":"10","key":"7_CR17","doi-asserted-by":"publisher","first-page":"2297","DOI":"10.1016\/j.jmva.2010.06.002","volume":"101","author":"R Harman","year":"2010","unstructured":"Harman, R., Lacko, V.: On decompositional algorithms for uniform sampling from n-spheres and n-balls. J. Multivar. Anal. 101(10), 2297\u20132304 (2010)","journal-title":"J. Multivar. Anal."},{"key":"7_CR18","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. NIPS Deep Learning and Representation Learning Workshop. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"7_CR19","unstructured":"Lopes, R.G., Fenu, S., Starner, T.: Data-free knowledge distillation for deep neural networks. NIPS Learn. Limited Labeled Data Workshop (LLD). arXiv preprint arXiv:1710.07535 (2017)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Muthukumar, V., Pedapati, T., Ratha, N., Sattigeri, P., Wu, C.W., Kingsbury, B.E.A.: Understanding unequal gender classification accuracy from face images. arXiv preprint arXiv:1812.00099 (2018)","DOI":"10.1109\/CVPRW.2019.00282"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you?: explaining the predictions of any classifier. In: Int. Conf. Knowl. Discovery Data Mining., pp. 1135\u20131144. ACM SIGKDD (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"7_CR22","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)"},{"key":"7_CR23","first-page":"1","volume":"1","author":"I Sanchez","year":"2015","unstructured":"Sanchez, I., Rocktaschel, T., Riedel, S., Singh, S.: Towards extracting faithful and descriptive representations of latent variable models. AAAI Spring Syposium Knowl. Represent. Reasoning 1, 1\u20134 (2015)","journal-title":"AAAI Spring Syposium Knowl. Represent. Reasoning"},{"key":"7_CR24","unstructured":"Xu, Z., Hsu, Y.-C., Huang, J.: Training shallow and thin networks for acceleration via knowledge distillation with conditional adversarial networks. arXiv preprint arXiv:1709.00513 (2017)"}],"container-title":["Lecture Notes in Computer Science","Advances in Intelligent Data Analysis XXI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30047-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:52:57Z","timestamp":1710359577000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30047-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031300462","9783031300479"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30047-9_7","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":"1 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IDA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Intelligent Data Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Louvain-la-Neuve","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","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":"12 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ida2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ida2023.org\/","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":"91","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":"38","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":"42% - 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":"3.1","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":"2.7","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}