BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Semi-Generative Modelling: Domain Adaptation with Cause and Effect
  Features - Julius von Kugelgen
DTSTART:20180523T103000Z
DTEND:20180523T110000Z
UID:TALK106336@talks.cam.ac.uk
CONTACT:Adrian Weller
DESCRIPTION:In this talk\, I will present a novel\, causally-inspired appr
 oach to domain adaptation which aims to also include unlabelled data in th
 e model fitting when labelled data is scarce. We consider a case of covari
 ate-shift adaptation with cause and effect features\, and–drawing from r
 ecent ideas in causal modelling and invariant prediction--show how this se
 tting leads to\, what we will refer to as\, a semi-generative model: P(Y\,
  X_eff |X_cau\, θ). Our proposed approach is robust to changes in the dis
 tribution over causal features\, and naturally allows to impose model cons
 traints by unsupervised learning of a map from causes to effects.\n In exp
 eriments on synthetic datasets we demonstrate a significant improvement in
  classification performance of our semi-generative model over purely-super
 vised and importance-weighting baselines when the amount of labelled data 
 is small. Moreover\, we apply our approach for regression on real-world pr
 otein-count data and compare it to feature transformation methods.\n\n\n\n
 Speaker bio:\nJulius von Kugelgen will be joining MLG as a new PhD student
  later this year\, as part of the Cambridge-Tuebingen programme.
LOCATION:Engineering Department\, CBL Room BE-438.
END:VEVENT
END:VCALENDAR