BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20261012T113950EDT-13988cluWv@132.216.98.100
DTSTAMP:20261012T153950Z
DESCRIPTION:CIM-SOCS talk\n\nHosted by: Yue Li\n\nSpeaker: Xiaoxiao Li\, Un
 iversity of British Columbia\n\nAbstract: Federated learning (FL) is a tre
 nding framework to enable multi-institutional collaboration in machine lea
 rning without sharing raw data. This presentation will discuss our ongoing
  progress in designing FL algorithms that embrace the data heterogeneity p
 roperties for multi-institutional data analysis in the FL setting.  I will
  present our algorithms for tackling feature and label heterogeneity\, mot
 ivated by our previous theoretical foundation. I will also show the promis
 ing results of applying our FL algorithms in healthcare applications. \n\n
 Bio: Dr. Xiaoxiao Li is an Assistant Professor at the Department of Electr
 ical and Computer Engineering (ECE) at the University of British Columbia 
 (UBC) starting August 2021. Before joining UBC\, Dr. Li was a Postdoc Rese
 arch Fellow in the Computer Science Department at Princeton University. Dr
 . Li obtained her PhD degree from Yale University in 2020. Dr. Li's resear
 ch interests range across the interdisciplinary fields of deep learning an
 d biomedical data analysis\, aiming to improve the trustworthiness of AI s
 ystems for healthcare. Dr. Li has had over 30 papers published in leading 
 machine learning conferences and journals\, including NeurIPS\, ICML\, ICL
 R\, MICCAI\, IPMI\, ECCV\, IEEE Transactions on Medical Imaging\, and Medi
 cal Image Analysis. Her work has been recognized with several best paper a
 wards at international conferences. \n
DTSTART:20221111T193000Z
DTEND:20221111T203000Z
LOCATION:MC 11\, McConnell Engineering Building\, CA\, QC\, Montreal\, H3A 
 0E9\, 3480 rue University
SUMMARY:Federated learning 
URL:https://www.mcgill.ca/cim/channels/event/federated-learning-351808
END:VEVENT
END:VCALENDAR