BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
PRODID:Data::ICal 0.24
BEGIN:VTIMEZONE
TZID:Pacific/Auckland
X-LIC-LOCATION:Pacific/Auckland
BEGIN:DAYLIGHT
DTSTART:19700927T020000
RRULE:FREQ=YEARLY;BYMONTH=9;BYDAY=-1SU
TZNAME:NZDT
TZOFFSETFROM:+1200
TZOFFSETTO:+1300
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19700405T030000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
TZNAME:NZST
TZOFFSETFROM:+1300
TZOFFSETTO:+1200
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:SMS Seminars
CONTACT:Dr Bogdan State
DESCRIPTION:Very large graphs are ubiquitous on the Internet\, and graph da
 ta is often essential to solving applied computational social science prob
 lems. One exceedingly common such problem is that of supervised classifica
 tion (or regression) on the nodes of edges of a graph. Picking a scalable 
 modeling strategy is a key practical challenge to solving such graph-based
  supervised machine learning problems. Broadly speaking\, modeling approac
 hes can be divided into attempts to model the graph structure explicitly (
 e.g. through Loopy Belief Propagation) or those approaches that use dimens
 ionality reduction (e.g. Non-Negative Matrix Factorization or Latent Diric
 hlet Allocation\, etc.) to extract node-level features. \n\nA more recent 
 development comes from the field of neural network research\, where severa
 l new techniques have been used to derive graph embeddings. In particular\
 , the use of automated differentiation has opened up new scalable ways of 
 thinking about graphs\, which also promise to revolutionize how we do rese
 arch on social networks. \n\nIn this workshop I will focus on learning gra
 ph embeddings using PyTorch\, a Python-based framework for stochastic comp
 utation. Because of the elegance of PyTorch's semantics (which include str
 aightforward integration with GPUs)\, graph embeddings generalize readily 
 to weighted and signed graphs\, as well as to hypergraphs. While packages 
 like PyTorch present us with a step change in our ability to process graph
  data\, they are still limited by computational resources: I will end my d
 iscussion with an overview of the challenges involved in processing graph 
 data at scale.\n\nAs there is limited capacity\, please register your inte
 rest here: http://vuw.qualtrics.com/jfe/form/SV_aVRjNwPaub3UKLb
DTEND;TZID=Pacific/Auckland:20180904T160000
DTSTAMP:20260403T185305Z
DTSTART;TZID=Pacific/Auckland:20180904T130000
LOCATION:CO238\, Cotton 238
ORGANIZER:Dr Bogdan State
SUMMARY:Dr Bogdan State - Embedding Relational Data using PyTorch
UID:seminar_sms927_20180827143121
URL:https://github.com/uchicago-computation-workshop/bogdan_state
END:VEVENT
END:VCALENDAR