{"id":5594,"date":"2026-01-16T07:59:48","date_gmt":"2026-01-16T07:59:48","guid":{"rendered":"https:\/\/conferences.sigappfr.org\/idc2026\/?post_type=speaker&p=5594"},"modified":"2026-05-12T07:51:13","modified_gmt":"2026-05-12T07:51:13","slug":"grigorios-tsoumakas","status":"publish","type":"speaker","link":"https:\/\/conferences.sigappfr.org\/idc2026\/speaker\/grigorios-tsoumakas\/","title":{"rendered":"Grigorios Tsoumakas"},"content":{"rendered":"
\n

\"\"<\/p>\n

Grigorios Tsoumakas<\/strong><\/h1>\n

Professor of Machine Learning and Knowledge Discovery at the School of Informatics of AUTH<\/h3>\n<\/div>\n\n\n

Dr. Grigorios Tsoumakas received a degree in Computer Science from the Aristotle University of Thessaloniki (AUTH), Greece, in 1999, an MSc in Artificial Intelligence from the University of Edinburgh, United Kingdom, in 2000 and a PhD in Computer Science from AUTH in 2005. He is a Professor of Machine Learning and Knowledge Discovery at the School of Informatics of AUTH since 2024, where he has also served as Associate Professor (2020-2024), Assistant Professor (2013 \u2013 2020) and Lecturer (2007 \u2013 2013). Since 2024, he also serves as an Affiliate Researcher at Archimedes\/RC Athena, Greece. In addition, he is co-founder and chief scientific officer at Medoid AI, a spin-off company of AUTH established in 2019, developing custom AI solutions based on cutting-edge Machine Learning technology. Dr. Tsoumakas is a senior member of ACM and IEEE. His research expertise focuses on supervised learning (ensemble methods, multi-target prediction, interpretablity) and natural language processing (semantic indexing, keyphrase extraction, summarization). He has published more than 180 research papers and according to Google Scholar he has more than 21.000 citations and an h-index of 54. His honors include receiving the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) 10-Year Test of Time Award in 2017 and the Marco Ramoni best paper award at the 19th International Conference on Artificial Intelligence in Medicine (AIME 2021).<\/p>\n\n\n

Title<\/strong>: Deep Multi-Label Classification<\/h2>\n

Abstract<\/strong>: This talk presents recent collaborative research endeavors of mine on the topic of multi-label learning with a focus on deep learning models. I will first discuss two methods that we have recently published for batch selection in the context of deep multi-label classification: i) by highlighting hard and imbalanced samples [1], and ii) by measuring uncertainty and modeling dynamic label correlations [2]. I will then share our latest developments on multi-label batch selection that achieves more efficient correlation modeling and leads to stronger predictive performance [3]. Finally, I will present a new method we have developed for extreme multi-label classification based on autoencoders [4].<\/p>\n

[1] Zhou, A., Liu, B., Peng, Z., Wang, J., & Tsoumakas, G. (2024). Multi-label Adaptive Batch Selection by\u00a0Highlighting Hard and\u00a0Imbalanced Samples. Lecture Notes in Computer Science, 14945 LNAI, 265\u2013281. https:\/\/doi.org\/https:\/\/doi.org\/10.1007\/978-3-031-70362-1_16<\/a><\/p>\n

[2] Zhou, A., Liu, B., Wang, J., & Tsoumakas, G. (2025). Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations. Proceedings of the AAAI Conference on Artificial Intelligence<\/em>, 39<\/em>(21), 22902\u201322909. https:\/\/doi.org\/10.1609\/aaai.v39i21.34452<\/a><\/p>\n

[3] Liu, B., Peng, H., Wei, Z., Zhang, J. & Tsoumakas, G. (2026) D2ACE: Multi-Label Batch Selection Guided by Dual Dynamics and Adaptive Correlation Enhancement. Proceedings of IJCAI-ECAI 2026 (accepted).<\/p>\n

[4] under double-blind review.<\/p>","protected":false},"excerpt":{"rendered":"

Grigorios Tsoumakas Professor of Machine Learning and Knowledge Discovery at the School of Informatics of AUTH Dr. Grigorios Tsoumakas received a degree in Computer Science from the Aristotle University of Thessaloniki (AUTH), Greece, in 1999, an MSc in Artificial Intelligence from…<\/p>\n","protected":false},"author":3,"featured_media":5595,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"speaker-category":[141],"speaker-tags":[109],"location":[150,142],"class_list":["post-5594","speaker","type-speaker","status-publish","has-post-thumbnail","hentry","speaker-category-keynote-speaker","speaker-tags-speaker","location-athens","location-greece"],"_links":{"self":[{"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/speaker\/5594","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/speaker"}],"about":[{"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/types\/speaker"}],"author":[{"embeddable":true,"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/comments?post=5594"}],"version-history":[{"count":2,"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/speaker\/5594\/revisions"}],"predecessor-version":[{"id":5628,"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/speaker\/5594\/revisions\/5628"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/media\/5595"}],"wp:attachment":[{"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/media?parent=5594"}],"wp:term":[{"taxonomy":"speaker-category","embeddable":true,"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/speaker-category?post=5594"},{"taxonomy":"speaker-tags","embeddable":true,"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/speaker-tags?post=5594"},{"taxonomy":"location","embeddable":true,"href":"https:\/\/conferences.sigappfr.org\/idc2026\/wp-json\/wp\/v2\/location?post=5594"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}