BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Cambridge Image Analysis Seminars
SUMMARY:Graph Neural Networks Use Graphs When They Shouldn
’t - Maya Bechler-Speicher\, Tel Aviv University
DTSTART;TZID=Europe/London:20241101T140000
DTEND;TZID=Europe/London:20241101T150000
UID:TALK222001AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/222001
DESCRIPTION:Predictions over graphs play a crucial role in var
ious domains\, including social networks and medic
ine.\nGraph Neural Networks (GNNs) have emerged as
the dominant approach for learning on graph data.
\nAlthough a graph-structure is provided as input
to the GNN\, in some cases the best solution can b
e obtained by ignoring it.\nWhile GNNs have the ab
ility to ignore the graph-structure in such cases\
, it is not clear that they will.\nIn this talk\,
I will show that GNNs actually tend to overfit the
given graph-structure. Namely\, they use it even
when a better solution can be obtained by ignoring
it.\nBy analyzing the implicit bias of gradient-d
escent learning of GNNs I will show that when the
ground truth function does not use the graphs\, GN
Ns are not guaranteed to learn a solution that ign
ores the graph\, even with infinite data.\nI will
prove that within the family of regular graphs\, G
NNs are guaranteed to extrapolate when learning wi
th gradient descent.\nThen\, based on our empirica
l and theoretical findings\, I will demonstrate on
real-data how regular graphs can be leveraged to
reduce graph overfitting and enhance performance.
Finally\, I will present a recent novel approach\,
Cayley Graph Propagation\, for propagating inform
ation over special types of regular graphs - the C
ayley graphs of the SL(2\, Zn) special linear grou
p\, to improve overfitting and information bottlen
ecks.
LOCATION:MR2 Centre for Mathematical Sciences
CONTACT:Ferdia Sherry
END:VEVENT
END:VCALENDAR