BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20211031T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20221030T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20220327T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.24879.field_data.0@www.diag.uniroma1.it
DTSTAMP:20260403T221422Z
CREATED:20220429T132909Z
DESCRIPTION:Abstract:  Machine learning on graphs is an important task with
  a plethora of cross-disciplinary applications\, ranging from recommender 
 systems to social network analysis and bioinformatics. The main challenge 
 here is to find appropriate representations of the graph structure that ca
 n easily be exploited by machine learning models. As a prominent recent pa
 radigm in graph analysis\, graph representation learning (GRL) aims at fin
 ding node embeddings in a way that the structure of the network and its va
 rious properties are preserved in the lower dimensional space representati
 ons. In this talk\, I will present our recent work in GRL\, focusing on mo
 dels that leverage random walks to capture rich structural semantics of re
 al-world graphs. I will also discuss practical applications of GRL\, inclu
 ding node classification\, link recommendation\, and data integration in b
 ioinformatics. Bio: Fragkiskos Malliaros (http://fragkiskos.me) is an Assi
 stant Professor at Paris-Saclay University\, CentraleSupélec and associate
  researcher at Inria Saclay. He also co-directs the M.Sc. Program in Data 
 Sciences and Business Analytics (CentraleSupélec and ESSEC Business School
 ). He was a postdoctoral researcher at UC San Diego (2016-17) and École Po
 lytechnique (2015-16). He received his Ph.D. in Computer Science from Écol
 e Polytechnique (2015) and his Diploma (2009) and M.Sc. (2011) degrees fro
 m the University of Patras\, Greece. He is the recipient of the 2012 Googl
 e European Doctoral Fellowship in Graph Mining\, the 2015 Thesis Prize by 
 École Polytechnique\, and best paper awards at TextGraphs-NAACL 2018 and A
 AAI ICWSM 2020 (honorable mention). In the past\, he has been the co-chair
  of various data science-related workshops. He has also presented twelve i
 nvited tutorials at international conferences in the areas of graph mining
  and data science (e.g.\, ICDM\, WSDM\, WWW\, EMNLP\, EDBT). His research 
 interests span the broad area of data science\, focusing on graph mining\,
  machine learning\, and graph-based information extraction.Also on Zoom me
 eting at:https://uniroma1.zoom.us/j/87288304331?pwd=ekkwWjBGUXZwcUozYTlvTG
 txV1J0UT09MeetingID: 872 8830 4331Passcode: 966243
DTSTART;TZID=Europe/Paris:20220504T110000
DTEND;TZID=Europe/Paris:20220504T110000
LAST-MODIFIED:20230915T092645Z
LOCATION:Aula Magna
SUMMARY:Learning graph representations with random walks: models and applic
 ations - Fragkiskos Malliaros
URL;TYPE=URI:https://www.diag.uniroma1.it/node/24879
END:VEVENT
END:VCALENDAR