{"679170":{"#nid":"679170","#data":{"type":"event","title":"School of CSE Seminar Series: Eli Chien","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ESpeaker:\u003C\/strong\u003E\u0026nbsp;Eli Chien, postdoctoral fellow at Georgia Tech\u003Cbr\u003E\u003Cstrong\u003EDate and Time:\u003C\/strong\u003E\u0026nbsp;March 28, 2:00-3:00 p.m.\u003Cbr\u003E\u003Cstrong\u003ELocation:\u003C\/strong\u003E\u0026nbsp;Coda, Room 230\u003Cbr\u003E\u003Cstrong\u003EHost:\u003C\/strong\u003E\u0026nbsp;Anqi Wu\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E\u0026nbsp;\u003Cem\u003EMachine Unlearning: The General Theory and LLM Practice of Privacy\u003C\/em\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract: \u003C\/strong\u003E\u201cThe right to be forgotten\u201d is the concept from GDPR that data holder (server) should erase the data and the corresponding derivatives whenever the original data providers (users) request for it. It is the common practice that LLM are trained on extensive and diverse dataset, which are usually generated from users. While retraining from scratch without those data is the gold standard, it is prohibitively costly. The goal of machine unlearning is to develop efficient approaches to approximate such gold standard, thus obeying the privacy regulation in laws like GDPR. In this talk, I will first introduce our empirical studies of unlearning for LLM, which highlight pitfalls of current empirical unlearning evaluation and weaknesses of heuristic methods. Then we will dive into the generic machine unlearning problem and my recent progress in unlearning theory.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBio:\u003C\/strong\u003E Eli Chien is currently a Postdoctoral Fellow at the Georgia Institute of Technology, working with Professor Pan Li. He obtained his Ph.D. from the University of Illinois, Urbana-Champaign, advised by Professor Olgica Milenkovic. His current research focuses on privacy in machine learning, including machine unlearning and differential privacy, as well as their applications to graph machine learning. His previous research centered on designing better graph neural networks with theoretical guarantees. His work has been primarily published in top-tier machine learning, data mining, and information theory venues, including ICML, NeurIPS, ICLR, Transactions on IT, KDD, TheWebConf, AISTATS, AAAI and more.\u003Cbr\u003E\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003ESpeaker:\u003C\/strong\u003E\u0026nbsp;Eli Chien, postdoctoral fellow at Georgia Tech\u003Cbr\u003E\u003Cstrong\u003EDate and Time:\u003C\/strong\u003E\u0026nbsp;March 28, 2:00-3:00 p.m.\u003Cbr\u003E\u003Cstrong\u003ELocation:\u003C\/strong\u003E\u0026nbsp;Coda, Room 230\u003Cbr\u003E\u003Cstrong\u003EHost:\u003C\/strong\u003E\u0026nbsp;Anqi Wu\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E\u0026nbsp;\u003Cem\u003EMachine Unlearning: The General Theory and LLM Practice of Privacy\u003C\/em\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"School of CSE hosts a seminar from Georgia Tech Postdoctoral Fellow Eli Chien"}],"uid":"36319","created_gmt":"2025-01-06 14:21:55","changed_gmt":"2025-03-20 13:17:21","author":"Bryant Wine","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2025-03-28T14:00:00-04:00","event_time_end":"2025-03-28T15:00:00-04:00","event_time_end_last":"2025-03-28T15:00:00-04:00","gmt_time_start":"2025-03-28 18:00:00","gmt_time_end":"2025-03-28 19:00:00","gmt_time_end_last":"2025-03-28 19:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Coda, Room 230","extras":[],"hg_media":{"675932":{"id":"675932","type":"image","title":"Eli Chien.png","body":null,"created":"1736173388","gmt_created":"2025-01-06 14:23:08","changed":"1736173388","gmt_changed":"2025-01-06 14:23:08","alt":"CSE Seminar Eli Chien","file":{"fid":"259612","name":"Eli Chien.png","image_path":"\/sites\/default\/files\/2025\/01\/06\/Eli%20Chien.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2025\/01\/06\/Eli%20Chien.png","mime":"image\/png","size":94935,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2025\/01\/06\/Eli%20Chien.png?itok=mE1neCzo"}}},"media_ids":["675932"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[],"keywords":[{"id":"166983","name":"School of Computational Science and Engineering"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EAnqi Wu (anqiwu@gatech.edu)\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}