[edm-announce] [EXTENDED DEADLINE] Call for papers: NIPS 2014 Workshop on Human Propelled Machine Learning
- From: Stephen Fancsali <sfancsali@xxxxxxxxx>
- To: edm-announce@xxxxxxxxxxxxx
- Date: Tue, 14 Oct 2014 14:26:52 -0400
[on behalf of Andrew Lan]
A NIPS 2014 Workshop
/Saturday, December 13, 2014
Montreal, Canada /
In typical applications of machine learning (ML), humans typically enter
the process at an early stage, in determining an initial representation
of the problem and in preparing the data, and at a late stage, in
interpreting and making decisions based on the results. Consequently,
the bulk of the ML literature deals with such situations. Much less
research has been devoted to ML involving "humans-in-the-loop," where
humans play a more intrinsic role in the process, interacting with the
ML system to iterate towards a solution to which both humans and
machines have contributed. In these situations, the goal is to optimize
some quantity that can be obtained only by evaluating human responses
and judgments. Examples of this hybrid, "human-in-the-loop" ML approach
include:
* ML-based education, where a scheduling system acquires information
about learners with the goal of selecting and recommending optimal
lessons;
* Adaptive testing in psychological surveys, educational assessments,
and recommender systems, where the system acquires testees'
responses and selects the next item in an adaptive and automated manner;
* Interactive topic modeling, where human interpretations of the
topics are used to iteratively refine an estimated model;
* Image classification, where human judgments can be leveraged to
improve the quality and information content of image features or
classifiers.
The key difference between typical ML problems and problems involving
"humans-in-the-loop" and is that in the latter case we aim to fit a
model of human behavior as we collect data from subjects and adapt the
experiments we conduct based on our model fit. This difference demands
flexible and robust algorithms and systems, since the resulting adaptive
experimental design depends on potentially unreliable human feedback
(e.g., humans might game the system, make mistakes, or act lazily or
adversarially). Moreover, the "humans-in-the-loop" paradigm requires a
statistical model for human interactions with the environment, which
controls how the experimental design adapts to human feedback; such
designs are, in general, difficult to construct due to the complex
nature of human behavior. Suitable algorithms also need to be very
accurate and reliable, since humans prefer a minimal amount of
interaction with ML systems; this aspect also prevents the use of
computationally intensive parameter selection methods (e.g., a simple
grid search over the parameter space). These requirements and real-world
constraints render "humans-in-the-loop" ML problems much more
challenging than more standard ML problems.
In this workshop, we will focus on the emerging new theories,
algorithms, and applications of human-in-the-loop ML algorithms.
Creating and estimating statistical models of human behavior and
developing computationally efficient and accurate methods will be a
focal point of the workshop. This human-behavior aspect of ML has not
been well studied in other fields that rely on human inputs such as
active learning and experimental design. We will also explore other
potential interesting applications involving humans in the loop in
different fields, including, for example, education, crowdsourcing,
mobile health, pain management, security, defense, psychology, game
theory, and economics.
The goal of this workshop is to bring together experts from different
fields of ML, cognitive and behavioral sciences, and human-computer
interaction (HCI) to explore the interdisciplinary nature of research on
this topic. In particular, we aim to elicit new connections among these
diverse fields, identify novel tools and models that can be transferred
from one to the other, and explore novel ML applications that will
benefit from the human-in-the-loop of ML algorithms paradigm. We believe
that a successful workshop will lead to new research directions in a
variety of areas and will also inspire the development of novel theories
and tools.
FORMAT
This workshop will consist of invited talks and paper
presentations/posters. We invite research from both academia and
industry to attend the workshop. As this is a workshop, there will be no
formal proceedings.
ORGANIZERS
* Richard G. Baraniuk, Rice University
* Michael C. Mozer, University of Colorado Boulder
* Divyanshu Vats, Rice University
* Christoph Studer, Cornell University
* Andrew E. Waters, Rice University and Openstax College
* Andrew S. Lan, Rice University
CALL FOR PAPERS
The NIPS 2014 workshop on Human Propelled Machine Learning will held in
conjunction with NIPS 2014 on Saturday, December 14, 2014, at the Palais
des Congrès de Montréal Convention and Exhibition Center in Montreal,
Quebec, Canada. We invite the submission of papers on all topics related
to machine learning problems involving one or more "humans-in-the-loop",
including but not limited to:
* Machine learning-based education
* Adaptive testing in psychological surveys, educational assessments,
and recommender systems
* Interactive topic modeling
* Computer vision with human collaboration
* Knowledge graph construction
* Other novel machine learning applications involving humans-in-the-loop
Submissions should follow the regular NIPS paper format. Papers
submitted for review do not need to be anonymized. Accepted papers will
be made available on the workshop website, since there will be no
official proceedings. Accepted papers will be presented either as a talk
or as a poster. We welcome submissions with either novel results that
have not been published previously or extensions of the authors'
previous work that has been recently published or is under review in
another conference or journal. In the interest of spurring the
discussion, we also encourage authors to submit extended abstracts and
work-in-progress papers with only preliminary results. For additional
information, please visit the workshop website:
http://dsp.rice.edu/HumanPropelledML_NIPS2014
PAPER SUBMISSION
Submissions will be judged on their novelty and potential impact in the
emerging field of human propelled machine learning.
Please send your submissions via email to hpml.nips2014@xxxxxxxxx
<mailto:hpml.nips2014@xxxxxxxxx>
Questions about the workshop can be sent to the same e-mail address.
IMPORTANT DATES
* Paper Submission: *EXTENDED to October 17, 2014 *
* Author notification: October 24, 2014
* Camera ready versions of accepted submissions: October 27, 2014
* Final workshop schedule: October 31, 2014
* Workshop: December 13, 2014
For more information about the NIPS conference, please visit
http://nips.cc/Conferences/2014
CONFIRMED SPEAKERS
* Emma Brunskill, Carnegie Mellon University
* Lawrence Carin, Duke University
* Todd Coleman, University of California, San Diego
* Jordan Boyd-Graber, University of Colorado Boulder
* Pedro Domingos, University of Washington
* Robert Nowak, University of Wisconsin Madison
* Devi Parikh, Virginia Tech
* Jacob Whitehill, HarvardX
* Beverly Park Woolf, University of Massachusetts Amherst
* Yisong Yue, California Institute of Technology
--
--------------------------
yours,
Andrew
Other related posts:
- » [edm-announce] [EXTENDED DEADLINE] Call for papers: NIPS 2014 Workshop on Human Propelled Machine Learning - Stephen Fancsali
