[PlanetKR] IJCAI 2017 Workshop on Logical Foundations for Uncertainty and Learning
Vaishak Belle
vaishak at cs.toronto.edu
Fri May 19 02:09:14 EST 2017
Dear colleagues, please note that we also invite previously published work
that is relevant to the theme of the workshop. (The deadline has been
extended.)
***
Call for Papers
IJCAI 2017 Workshop on Logical Foundations for Uncertainty and Learning
http://homepages.inf.ed.ac.uk/vbelle/workshops/lfu17/
Overview
The purpose of this workshop is to promote logical foundations for
reasoning and learning under uncertainty. Uncertainty is inherent in many
AI applications, and coping with this uncertainty, in terms of preferences,
probabilities and weights, is essential for the system to operate
purposefully. In the same vein, expecting a domain modeler to completely
characterize a system is often unrealistic, and so enabling mechanisms by
means of which the system can infer and learn about the environment is
needed. While probabilistic reasoning and Bayesian learning has enjoyed
many successes and is central to our current understanding of the data
revolution, a deeper investigation on the underlying semantical issues as
well as principled ways of extending the frameworks to richer settings is
what this workshop strives for. Broadly speaking, we aim to bring together
the many communities focused on uncertainty reasoning and learning --
including knowledge representation, machine learning, logic programming and
databases -- by focusing on the logical underpinnings of the approaches and
techniques.
Given the intent of the workshop, we encourage two categories of
submissions:
-
On the practical side, we solicit papers that propose ways to bridge
conventional learning and inference techniques with deductive and inductive
reasoning. Driven by the successes of relational graphical models and
statistical relational learning, we especially encourage papers that
emphasize or demonstrate non-standard logical features in systems, e.g. the
ability to handle infinite domains, existential uncertainty and/or function
symbols.
-
On the foundations side, we solicit papers that explicate the use of
weights in reasoning and learning, e.g. the use of weight functions such as
degrees of belief, preferences, and truth degrees. We especially encourage
papers that demonstrate how non-standard weight functions for reasoning and
learning can be better integrated with existing probabilistic methods. The
idea, then, is to foster collaboration between machine learning
practitioners and the weighted logic community. For example, we encourage
papers that revisit the learning objectives and inference methodologies of
existing systems, and propose novel semantical frameworks to understand
them.
In essence, this workshop builds on and extends the scope of the successful
series WL4AI (Weighted Logics for Artificial Intelligence: ECAI-2012,
IJCAI-2013, IJCAI-2015) in additionally looking at the semantical
foundations of machine learning and exploring practical issues.
Topics include (but are not limited to):
-
Probabilistic and weighted databases and knowledge bases
-
Integration of deductive and inductive reasoning with Bayesian inference
and learning
-
Semantical foundations for machine learning
-
Logics for data-intensive information processing, such as data fusion
-
Extension of statistical relational learning with generic weight
functions
-
Declarative methods for inference and learning
Paper Format and Submission
We invite technical papers (up to 6 pages), position papers (up to 2
pages).
We invite submissions describing either work in progress or mature work
that has already been published at other research venues and would be of
interest to researchers working on the themes above. Submission of
previously published work in whole or in part may be in the form of a
resubmission of a previous paper, or in the form of a position paper that
overviews and cites a body of work.
All papers should be typeset in the IJCAI style, described at
http://ijcai-17.org/FormattingGuidelinesIJCAI-17.zip
Papers should be submitted via EasyChair at
https://easychair.org/conferences/?conf=lfu17
Please see the website for up to date information (including submission
procedure):
http://homepages.inf.ed.ac.uk/vbelle/workshops/lfu17/
Important Dates
-
Paper Submission: May 28 (extended from May 15)
-
Author Notification: June 8
-
Camera ready: July 15
-
Workshop Date: August 19
Organizing Committee
Vaishak Belle, University of Edinburgh, vaishak(at)ed.ac.uk
Marcelo Finger, University of Sao Paulo, mfinger(at)ime.usp.br
James Cussens, University of York, james.cussens(at)york.ac.uk
Guilin Qi, Southeast University, China, gqi(at)seu.edu.cn
Henri Prade, Universite Paul Sabatier, France, prade(at)irit.fr
Lluis Godo, IIIA CSIC, Spain, godo(at)iiia.csic.es
Program Committee
Fabio Cozman, University of Sao Paulo, Brazil
Jesse Davies, KU Leuven, Belgium
Adnan Darwiche, UCLA, USA
Didier Dubois, IRIT, France
Esra Erdem, Sabanci University, Turkey
Linda van der Gaag, Universiteit Utrecht, The Netherlands
Tommaso Flaminio, University of Insubria, Italy
Vibhav Gogate, University of Texas at Dallas, USA
Joe Halpern, Cornell University, USA
Manfred Jaeger, Aalborg University, Denmark
Souhila Kaci, University Montpellier, France
Gabriele Kern-Isberner, Technical University of Dortmund, Germany
Gerhard Lakemeyer, RWTH Aachen University, Germany
Churn-Jung Liau, Academia Sinica, Taiwan
Emiliano Lorini, IRIT, France
Thomas Lukasiewicz, University of Oxford, UK
Carsten Lutz, University of Bremen, Germany
Denis Maua, University of Sao Paulo, Brazil
Vanina Martinez, Universidad Nacional del Sur, Argentina
Zoran Ognjanovic, Mathematical Institute SANU, Serbia
Ron Petrick, Edinburgh, UK
Rodrigo De Salvo Braz, SRI, USA
Giuseppe Sanfilippo, Univ. Catania, Italy
Steven Schockaert, Cardiff University, UK
Guillermo Simari, Universidad Nacional del Sur, Argentina
Umberto Straccia, CNR, Italy
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://discuss.it.uts.edu.au/pipermail/planetkr/attachments/20170518/f4a8df14/attachment-0001.html
More information about the PlanetKR
mailing list