[Seminar] Fairness and Graph Deep Generation through the Lens of Time
Friday, March 11, 2022
11:00 am - 12:00 pm
Speaker
Wenbin
Zhang
Postdoctoral
Associate
Carnegie
Mellon
University
Location
Virtual
via
Zoom*
*Microsoft
365
@cougarnet.uh.edu
authentication
required
to
join
via
Zoom
Abstract
Many
problems
in
machine
learning
are
time-dependent
in
nature,
which
brings
unique
and
complicated
challenges
such
as
uncertainty
on
the
event
of
interest
and
the
mutual
interactions
among
static
and
dynamic
patterns.
To
overcome
these
challenges,
devising
new
techniques
becomes
essential.
In
this
talk,
I
will
be
showing
some
of
these
new
techniques
through
some
machine
learning
problems
I
have
recently
worked
on,
such
as
fairness
under
uncertainty
to
support
social
fairness,
and
a
generic
framework
of
factorized
deep
generative
models
for
interpretable
dynamic
graph
generation,
which
provide
necessary
complements
to
these
important
yet
challenging
tasks.
About the Speaker
Wenbin
Zhang
is
a
Postdoctoral
Associate
at
Carnegie
Mellon
University,
and
an
Associate
Member
at
the
Te
Ipu
o
te
Mahara
Artificial
Intelligence
Institute.
He
received
his
Ph.D.
from
the
University
of
Maryland,
Baltimore
County,
and
has
been
a
visiting
researcher
at
various
global
research
centers
and
institutions.
His
research
investigates
the
theoretical
foundations
of
machine
learning
with
a
focus
on
societal
impact
and
welfare.
Other
interests
include
deep
generative
models
and
health
informatics
with
an
academic
track
record
across
computer
science
and
interdisciplinary
venues,
such
as
IJCAI,
ICDM,
AAAI,
SDM,
Climate
Dynamics
as
well
as
Radiotherapy
and
Oncology.
