2018 Conference on Fairness, Accountability, and
Transparency (FAT*)
The first FAT* conference will be held February 23 and 24th, 2018 at New York
University, NYC. Algorithmic systems are being adopted in a growing number of
contexts. Fueled by big data, these systems filter, sort, score, recommend,
personalize, and otherwise shape human experiences of socio-technical systems.
Although these systems bring myriad benefits, they also contain inherent risks,
such as codifying and entrenching biases; reducing accountability and hindering
due process; and increasing the information assymmetry between data producers
and data holders.
FAT* is an annual conference dedicating to bringing together a diverse
community to investigate and tackle issues in this emerging area. Topics of
interest include, but are not limited to:
The theory and practice of fair and interpretable Machine Learning, Information
Retrieval, NLP, and Computer Vision
Measurement and auditing of deployed systems
Users' experience of algorithms, and design interventions to empower
users
The ethical, moral, social, and policy implications of big data and ubiquitous
intelligent systems
FAT* builds upon several years of successful workshops on the topics of
fairness, accountability, transparency, ethics, and interpretability in machine
learning, recommender systems, the web, and other technical disciplines.
Important Dates
Paper registration: September 29, 2017, 23:59 Anywhere on Earth (AoE)
Paper submission: October 6, 2017, 23:59 Anywhere on Earth (AoE)
Notification: November 17, 2017
Camera ready: December 17, 2017
Conference: February 23-24, 2018
Topics of Interest
FAT* is an international and interdisciplinary peer-reviewed conference that
seeks to publish and present work examining the fairness, accountability, and
transparency of algorithmic systems. The FAT* conference solicits work from a
wide variety of disciplines, including computer science, statistics, the
humanities, and law. FAT* welcomes submissions that touch on any of the
following topics (broadly construed):
Fairness
Techniques and models for fairness-aware data mining, information
retrieval, recommendation, etc.
Formalizations of fairness, bias, discrimination, etc.
Translation of legal and ethical models of fairness into mathematical
objectives
User and experimental studies on perceptions of algorithmic bias and
unfairness
Design interventions to mitigate biases in systems, or discourage biased
behavior from users
Measurement and data collection regarding potential unfairness in systems
Position and policy papers on how to design socially responsible and equitable
systems
Accountability
Processes and strategies for developing accountable systems
Methods and tools for ensuring that algorithms comply with fairness
policies
Metrics for measuring unfairness and bias in different contexts
Techniques for guaranteeing accountability without necessitating
transparency
Techniques for ethical autonomous and A/B testing
Privacy of user data
Position and policy papers on the design and implementation of accountability
regimes for systems
Transparency
Interpretability of machine learning models
Generation of explanations for algorithmic outputs
Design strategies for communicating the logic behind algorithmic systems
User and experimental studies on the effectiveness of algorithm transparency
techniques
Tools and methodologies for conducting algorithm audits
Empirical results from algorithm audits
Frameworks for conducting ethical and legal algorithm audits
This list of topics is not meant to be all-inclusive. Authors who are unclear
about whether their work falls within the purview of the FAT* conference should
contact the PC Chairs for clarification.
Tracks
To ensure that all submissions to FAT* are reviewed by a knowledgable and
appropriate set of reviewers, the conference is divided into tracks. Authors
must choose from the following tracks when they register their
submissions:
Theory and Security
Statistics, Machine Learning, Data Mining, NLP, and Computer Vision
Programming Languages, Databases, and other Systems (Recommender, Information
Retrieval, etc.)
Visualization, Human Computer Interaction, and User Studies
Measurement and Algorithm Audits
Law, Policy, and Social Science
Archival and Non-archival
FAT* 2018 offers authors the choice of archival and non-archival paper
submissions. Archival papers will appear in the published proceedings of the
conference, if they are accepted; conversely, accepted non-archival papers will
only appear as abstracts in the proceedings. FAT* offers a non-archival option
to avoid precluding the future submission of these papers to area-specific
journals. Note that all submissions will be judged by the same quality
standards, regardless of whether the authors choose the archival or
non-archival option. Furthermore, reviewers will not be told whether
submissions under review are archival or not, to avoid influencing their
evaluations.
Authors of all accepted papers must present their work at the FAT* 2018
conference, regardless of whether their paper is archival or
non-archival.
Further information is available at https://fatconference.org/2018/cfp.html
