BEGIN:VCALENDAR METHOD:REQUEST PRODID:Microsoft Exchange Server 2010 VERSION:2.0 BEGIN:VTIMEZONE TZID:Eastern Standard Time BEGIN:STANDARD DTSTART:16010101T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=11 END:STANDARD BEGIN:DAYLIGHT DTSTART:16010101T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=2SU;BYMONTH=3 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT ORGANIZER;CN="Satterfield, Mary Ann":mailto:msaterfi@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=ecefaculty @ecn.purdue.edu:mailto:ecefaculty@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=ececourtes y-list@ecn.purdue.edu:mailto:ececourtesy-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=ecegradstu dent-list@ecn.purdue.edu:mailto:ecegradstudent-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=ecepostdoc s-list@ecn.purdue.edu:mailto:ecepostdocs-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN='CE Area F aculty':mailto:ececompfaculty-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Sundaram, Shreyas":mailto:sundara2@purdue.edu ATTACH:CID:image001.png@01D818E3.C0A87D20 DESCRIPTION;LANGUAGE=en-US:Host: Maggie Zhu ~ zhu0@purdue.edu\n\nFaculty Candidate Seminar – Autonomous and Connected Syst ems\n\n[cid:image001.png@01D818E3.C0A87D20]Luana Ruiz\nPh.D. Candidate\nDe pt. of Electrical and Systems Engineering\nUniversity of Pennsylvania\n\nT hursday\, Feb. 10\, 2022\nPresentation: 10:30 A.M. – 11:30 A.M.\nQ & A: 11:30 A.M. – 12:00 P.M.\nPurdue Graduate Student Center\n504 Northwest ern Ave. ~ Room 105A & B\nhttps://purdue-edu.zoom.us/meeting/93351017078\n \nMachine Learning on Large-Scale Graphs\n\n\nAbstract: Graph neural netw orks (GNNs) are successful at learning representations from most types of network data but suffer from limitations in large graphs\, which do not ha ve the Euclidean structure that time and image signals have in the limit. Yet\, large graphs can often be identified as being similar to each other in the sense that they share structural properties. Indeed\, graphs can be grouped in families converging to a common graph limit -- the graphon. A graphon is a bounded symmetric kernel which can be interpreted as both a r andom graph model and a limit object of a convergent sequence of graphs. G raphs sampled from a graphon almost surely share structural properties in the limit\, which implies that graphons describe families of similar graph s. We can thus expect that processing data supported on graphs associated with the same graphon should yield similar results. In my research\, I for malize this intuition by showing that the error made when transferring a G NN across two graphs in a graphon family is small when the graphs are suff iciently large. This enables large-scale graph machine learning by transfe rence: training GNNs on moderate-scale graphs and executing them on large- scale graphs.\n\n\n\nBio: Luana Ruiz received the B.Sc. degree in electri cal engineering from the University of São Paulo\, Brazil\, and the M.Eng . degree in electrical engineering from the École Supérieure d'Electrici té (now CentraleSupélec)\, France\, in 2017. She is currently a Ph.D. ca ndidate with the Department of Electrical and Systems Engineering at the U niversity of Pennsylvania. Her primary research interests are in large-sca le graph machine learning and the mathematical foundations of deep learnin g. Luana was awarded an Eiffel Excellence scholarship from the French Mini stry for Europe and Foreign Affairs between 2013 and 2015\, and nominated an iREDEFINE fellow in 2019 and a MIT EECS Rising Star in 2021. She has al so received two Best Student Paper awards at the European Signal Processin g Conference (EUSIPCO)\, in 2019 and 2021.\n UID:040000008200E00074C5B7101A82E0080000000010C7AAC0E318D801000000000000000 0100000001332CD0F39147F4882A2A0A2AA97C0A8 SUMMARY;LANGUAGE=en-US:ACS Faculty Candidate Luana Ruiz\, PhD Candidate. UP enn: Machine Learning on Large-Scale Graphs DTSTART;TZID=Eastern Standard Time:20220210T103000 DTEND;TZID=Eastern Standard Time:20220210T120000 CLASS:PUBLIC PRIORITY:5 DTSTAMP:20220203T145311Z TRANSP:OPAQUE STATUS:CONFIRMED SEQUENCE:0 LOCATION;LANGUAGE=en-US:PGSC\, Room 105A & B X-MICROSOFT-CDO-APPT-SEQUENCE:0 X-MICROSOFT-CDO-OWNERAPPTID:-366794778 X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY X-MICROSOFT-CDO-ALLDAYEVENT:FALSE X-MICROSOFT-CDO-IMPORTANCE:1 X-MICROSOFT-CDO-INSTTYPE:0 X-MICROSOFT-DONOTFORWARDMEETING:FALSE X-MICROSOFT-DISALLOW-COUNTER:FALSE X-MICROSOFT-LOCATIONS:[{"DisplayName":"PGSC\, Room 105A & B"\,"LocationAnno tation":""\,"LocationUri":""\,"LocationStreet":""\,"LocationCity":""\,"Loc ationState":""\,"LocationCountry":""\,"LocationPostalCode":""\,"LocationFu llAddress":""}] BEGIN:VALARM DESCRIPTION:REMINDER TRIGGER;RELATED=START:-PT15M ACTION:DISPLAY END:VALARM END:VEVENT END:VCALENDAR