Connectionists: CFP: 3rd Workshop on Fairness, Accountability, and Transparency in Machine Learning

[Sorelle Friedler]

CALL FOR PAPERS

=========================================================================

3rd Workshop on Fairness, Accountability, and Transparency in Machine
Learning

Co-located with the Data Transparency Lab 2016

November 18, New York, NY

http://fatml.org/

Submission Deadline: September 9, 2016

=========================================================================

OVERVIEW

--------

This workshop aims to bring together a growing community of researchers and
practitioners concerned with fairness, accountability, and transparency in
machine learning. The past few years have seen growing recognition that
machine learning raises novel challenges for ensuring non-discrimination,
due process, and understandability in decision-making. In particular,
policymakers, regulators, and advocates have expressed fears about the
potentially discriminatory impact of machine learning, with many calling
for further technical research into the dangers of inadvertently encoding
bias into automated decisions. At the same time, there is increasing alarm
that the complexity of machine learning may reduce the justification for
consequential decisions to “the algorithm made me do it.” The goal of this
workshop is to provide researchers with a venue to explore how to
characterize and address these issues with computationally rigorous
methods.

This year, the workshop is co-located with two other highly related events:
the Data Transparency Lab (DTL) Conference and the Workshop on Data and
Algorithmic Transparency (DAT). We anticipate that our workshop will
consist of a mix of invited talks, invited panels, and contributed talks.
We welcome paper submissions that address any issue of fairness,
accountability, and transparency related to machine learning, especially
those that provide a bridge to empirical studies of the behavior of
data-driven systems in the wild, the focus of the DTL and DAT events.

TOPICS OF INTEREST

------------------

Fairness:

   1.

   Can we develop new computational techniques for discrimination-aware
   data mining? How should we handle, for example, bias in training data sets?
   2.

   How should we formalize fairness? What does it mean for an algorithm to
   be fair?
   3.

   Should we look only to the law for definitions of fairness? Are legal
   definitions sufficient? Can legal definitions even be translated to
   practical algorithmic contexts?
   4.

   Can we develop definitions of discrimination and disparate impact that
   move beyond the Equal Employment Opportunity Commission’s 80% rule?
   5.

   Who decides what counts as fair when fairness becomes a machine learning
   objective?
   6.

   Are there any dangers in turning questions of fairness into
   computational problems?


Accountability:

   1.

   What would human review entail if models were available for direct
   inspection?
   2.

   Are there practical methods to test existing algorithms for compliance
   with a policy?
   3.

   Can we prove that an algorithm behaves in some way without having to
   reveal the algorithm? Can we achieve accountability without transparency?
   4.

   How can we conduct reliable empirical black-box testing and/or reverse
   engineer algorithms to test for ethically salient differential treatment?
   5.

   What are the societal implications of autonomous experimentation? How
   can we manage the risks that such experimentation might pose to users?


Transparency:

   1.

   How can we develop interpretable machine learning methods that provide
   ways to manage the complexity of a model and/or generate meaningful
   explanations?
   2.

   Can we use adversarial conditions to learn about the inner workings of
   inscrutable algorithms? Can we learn from the ways they fail on edge cases?
   3.

   How can we use game theory and machine learning to build fully
   transparent, but robust models using signals that people would face severe
   costs in trying to manipulate?



PAPER SUBMISSION

----------------


Papers are limited to 4 content pages, including figures and tables, and
should use a standard 2-column 11pt format; however, an additional fifth
page containing only cited references is permitted. Papers must be
anonymized for double-blind reviewing. Accepted papers will be made
available on the workshop website and should also be posted by the authors
to arXiv; however, the workshop's proceedings can be considered
non-archival, meaning that contributors are free to publish their work in
archival journals or conferences. Accepted papers will be either presented
as a talk or poster (to be determined by the workshop organizers).

Papers should be submitted here:
https://easychair.org/conferences/?conf=fatml2016

Complete Paper Submissions Due: September 9, 2016, 11:59:59PM EDT

Notification to Authors: October 7, 2016

Camera-Ready Papers Due: October 28, 2016


RELATED CALL

------------

Authors of especially well developed papers should also consider submitting
to a special issue of Big Data on “Social and Technical Trade-Offs,” which
is being guest edited by a number of the workshop organizers:
http://www.liebertpub.com/lpages/big-data-cfp-social-and-technical-trade-offs/155/

Complete Manuscript Submissions Due: September 15, 2016


ORGANIZATION

------------

Workshop Organizers:

Solon Barocas, Microsoft Research NYC

Sorelle Friedler, Haverford College

Moritz Hardt, Google

Joshua Kroll, CloudFlare

Suresh Venkatasubramanian, University of Utah

Hanna Wallach, Microsoft Research NYC


Program Committee:

Sorelle Friedler, Haverford College, Co-Chair
Suresh Venkatasubramanian, University of Utah, Co-Chair


Anupam Datta, Carnegie Mellon University

Hal Daume, University of Maryland, College Park

Fernando Diaz, Microsoft Research NYC
Krishna Gummadi, MPI-SWS

Sara Hajian, Eurecat, Technology Center of Catalonia

Kristian Lum, Human Rights Data Analysis Group

David Robinson, Upturn

Salvatore Ruggieri, Università di Pisa

Julia Stoyanovich, Drexel University
Christo Wilson, Northeastern University

*** more members may be added ***
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20160810/600f386c/attachment-0001.html>