{"id":565,"date":"2022-05-07T15:49:37","date_gmt":"2022-05-07T15:49:37","guid":{"rendered":"https:\/\/deel.quebec\/projets\/axe3-interpretabilite\/projet-5\/"},"modified":"2022-06-16T13:10:22","modified_gmt":"2022-06-16T13:10:22","slug":"projet-5","status":"publish","type":"projets","link":"https:\/\/deel.quebec\/en\/projets\/axe3-interpretabilite\/projet-5\/","title":{"rendered":"Can column generation be used for generating explanations in machine learning?"},"content":{"rendered":"<h3><b>Generating explainable predictions using column generation<\/b><\/h3>\n<h6><span style=\"font-weight: 400;\">ONGOING<\/span><\/h6>\n<p><span style=\"font-weight: 400;\">This project is concerned with producing interpretable predictions for a multiclass classification problem.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">There has been some research using column generation to perform binary classification to generate Boolean decision rules in Disjunctive Normal Form as explanations. We extend this binary classification model to a multiclass classification task by following the classical one-vs-rest approach. One of the major challenges in the project is to assign weights (which also needs to be interpretable) when more than one class is tested positive in the one-vs-rest framework.\u00a0<\/span><\/p>\n<p><strong>Team<\/strong><\/p>\n<ul>\n<li><span style=\"font-weight: 400;\">Krunal Patel (PhD Student),<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Andrea Lodi (Professor)<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Guy Desaulniers (Professor)<\/span><\/li>\n<li><i><span style=\"font-weight: 400;\">Thales Group (Industrial partner)<\/span><\/i><\/li>\n<\/ul>\n<p><strong>Datasets used for experiments : <\/strong><\/p>\n<ul>\n<li><span style=\"font-weight: 400;\">NOTAM (NOtice To AirMen)\u00a0<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">Dataset supplied by Thales Group. The data contains the messages sent to alert aircraft pilots of potential hazards along a flight route or at a location that could affect the safety of the flight.<\/span><\/p>\n<p><strong>R\u00e9f\u00e9rence<\/strong><\/p>\n<p><span style=\"font-weight: 400;\">Dash, S., Gunluk, O., &amp; Wei, D. (2018). Boolean Decision Rules via Column Generation. <\/span><i><span style=\"font-weight: 400;\">Advances in Neural Information Processing Systems<\/span><\/i><span style=\"font-weight: 400;\">, <\/span><i><span style=\"font-weight: 400;\">31<\/span><\/i><span style=\"font-weight: 400;\">, 4655-4665. <\/span><a href=\"https:\/\/papers.nips.cc\/paper\/2018\/hash\/743394beff4b1282ba735e5e3723ed74-Abstract.html\"><span style=\"font-weight: 400;\">Lien<\/span><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"Generating explainable predictions using column generation ONGOING This project is concerned with producing interpretable predictions","protected":false},"featured_media":287,"parent":478,"menu_order":32,"template":"","_links":{"self":[{"href":"https:\/\/deel.quebec\/en\/wp-json\/wp\/v2\/projets\/565"}],"collection":[{"href":"https:\/\/deel.quebec\/en\/wp-json\/wp\/v2\/projets"}],"about":[{"href":"https:\/\/deel.quebec\/en\/wp-json\/wp\/v2\/types\/projets"}],"up":[{"embeddable":true,"href":"https:\/\/deel.quebec\/en\/wp-json\/wp\/v2\/projets\/478"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/deel.quebec\/en\/wp-json\/wp\/v2\/media\/287"}],"wp:attachment":[{"href":"https:\/\/deel.quebec\/en\/wp-json\/wp\/v2\/media?parent=565"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}