Extreme classification is a rapidly growing research area within machine learning focusing on
\nmulti-class and multi-label problems involving an extremely large number of labels (even more
\nthan a million). Many applications of extreme classification have been found in diverse areas
\nranging from language modeling to document tagging in NLP, face recognition to learning universal feature representations in computer vision, gene function prediction in bioinformatics, etc.
\nExtreme classification has also opened up a new paradigm for key industrial applications such
\nas ranking and recommendation by reformulating them as multi-label learning tasks where each
\nitem to be ranked or recommended is treated as a separate label. Such reformulations have led to
\nsignificant gains over traditional collaborative filtering and content-based recommendation techniques. Consequently, extreme classifiers have been deployed in many real-world applications in
\nindustry.<\/p>\n
Extreme classification has raised many new research challenges beyond the pale of traditional
\nmachine learning including developing log-time and log-space algorithms, deriving theoretical
\nbounds that scale logarithmically with the number of labels, learning from biased training data,
\ndeveloping performance metrics, etc. The seminar aimed at bringing together experts in machine
\nlearning, NLP, computer vision, web search and recommendation from academia and industry
\nto make progress on these problems. We believe that this seminar has encouraged the interdisciplinary collaborations in the area of extreme classification, started discussion on identification
\nof thrust areas and important research problems, motivated to improve the algorithms upon the
\nstate-of-the-art, as well to work on the theoretical foundations of extreme classification.<\/p>\n","protected":false},"excerpt":{"rendered":"
Extreme classification is a rapidly growing research area within machine learning focusing on multi-class and multi-label problems involving an extremely large number of labels (even more than a million). Many applications of extreme classification have been found in diverse areas ranging from language modeling to document tagging in NLP, face recognition to learning universal feature […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13561,13556,13562,13545],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1123782","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2018-7-15","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2025\/01\/bengio19.pdf","id":"1123785","title":"bengio19","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":1123785,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2025\/01\/bengio19.pdf"}],"msr-author-ordering":[{"type":"text","value":"Samy Bengio","user_id":0,"rest_url":false},{"type":"guest","value":"krzysztof-dembczynski","user_id":793031,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=krzysztof-dembczynski"},{"type":"guest","value":"thorsten-joachims-2","user_id":899907,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=thorsten-joachims-2"},{"type":"text","value":"Marius Kloft","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Manik Varma","user_id":32791,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Manik Varma"}],"msr_impact_theme":[],"msr_research_lab":[199562],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1123782","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1123782\/revisions"}],"predecessor-version":[{"id":1123788,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1123782\/revisions\/1123788"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1123782"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=1123782"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1123782"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1123782"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1123782"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=1123782"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1123782"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=1123782"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=1123782"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1123782"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1123782"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1123782"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1123782"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1123782"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1123782"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1123782"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}