Outlier Detection De-constructed

ODD v5.0 2018


Data Mining & Analysis



CFP: 5th ACM SIGKDD Workshop on Outlier Detection De-constructed
-----------------------------------------------------------------------------------------------------------------------------
ODD v5.0 @ KDD 2018
Workshop on Outlier Detection De-constructed
will be held in conjunction with KDD 2018
August 20, 2018 in London, UK
http://www.andrew.cmu.edu/user/lakoglu/odd/index.html
-----------------------------------------------------------------------------------------------------------------------------
ODD v5.0 is a full day workshop, organized in conjunction with ACM SIGKDD 2018.
We build on the successful series of past four ODD Workshops that have been organized at ACM KDD 2016, KDD 2015, KDD 2014, and KDD 2013.
The main goal of the ODD workshop is to bring together academics, industry and government researchers and practitioners to discuss and reflect on outlier mining challenges.
This year, our workshop is motivated by the need for new means to de-construct the black-box nature of outlier detection methods. Such new techniques are to offer solutions for flagged outliers to be interpreted, adopted, trusted, and safely used by decision makers in mission-critical applications. By de-construction we mean the process of tracing the contribution of each input to the output (for one or more given examples) and evaluate to which extent a particular input would move the output due to inherited variations.
While we aim for a focus on the theme of explanations (for complex models), we welcome papers addressing any other challenges at large of the subject area.
The glossary definitions of the word deconstruct include “analyze (a text or a linguistic or conceptual system) by deconstruction, typically in order to expose its hidden internal assumptions and contradictions and subvert its apparent significance or unity” and “reduce (something) to its constituent parts in order to reinterpret it”. This is exactly what the ODD v5.0 workshop focuses on in the context of outlier mining, that is, identifying the constituent parts of a detection model to expose its hidden/underlying reasoning to flag an outlier.
ODD v5.0 (2018) aims to increase awareness of the community to the following topics on outlier mining:
How can we (verbally or visually) explain the reasoning behind the decisions of various outlier detection models?
What techniques can be used for identifying root causes and generating mechanisms of outliers for diagnosis and treatment?
What is the extent to which we can draw causal (i.e. beyond descriptive) explanations to the emergence of outliers?
How can we create an ensemble of outlier detectors that is interpretable?
How can we employ novel deep learning models for outlier detection?
How can we apply recurrent models to outlier detection in complex data such as graph or text data streams?
How can we design explanation techniques for complex detectors such as deep models as well as ensemble methods?
How can we leverage interactions with human experts to mine outliers?
How can we incorporate complex user feedback for outlier detection?
IMPORTANT DATES
---------------------------
Submission deadline: May 8, 2018, 23:59 PST
Acceptance notification: June 8, 2018, 23:59 PST
Camera-ready deadline: June 22, 2018, 23:59 PST
Workshop day: Aug 20, 2018
TOPICS OF INTEREST
--------------------------------
Topics of interests for the proposed workshop include, but are not limited to:
interleaved detection and description of outliers
explanation models for given outliers
quantitative input influence measures for outlier detection models
pattern and local information based outlier description
subspace outliers, feature selection, and space transformations
ensemble methods for outlier detection
deep neural network models for outlier detection
explanation techniques for complex/black-box detectors
identification of outlier rules
descriptive local outlier ranking
finding intensional knowledge
contrast mining and causality analysis
visualizations for outlier mining results
visual analytics for interactive detection and evaluation of outliers
human-in-the-loop modeling and learning
comparative studies on outlier description
decision rule set mining for outliers
Application areas of interest include, but are not limited to:
fraud detection, and data logs
fake news and misinformation
healthcare analysis, and other sensor databases
security and surveillance, and other streaming databases
user behavior analysis, and other transactional data sources
process logs, and other sequential or ordered data
social networks, and other graph databases
We encourage submissions describing innovative work in related fields that address the issue of interpretability in outlier mining.
SUBMISSION GUIDELINES
-------------------------------------
We invite submission of unpublished original research papers that are not under review elsewhere. All papers will be peer reviewed. If accepted, at least one of the authors must attend the workshop to present their work. The submitted papers must be written in English and formatted according to the ACM Proceedings Template (Tighter Alternate style) available at:
https://www.acm.org/publications/proceedings-template-16dec2016
The maximum length of papers is 9 pages in this format. We also invite vision papers and descriptions of work-in-progress or case studies on benchmark data as short paper submissions of up to 4 pages.
The papers should be in PDF format and submitted via EasyChair submission site
https://easychair.org/conferences/?conf=oddv50
Accepted papers will be included in the KDD 2018 Digital Proceedings, and made available in the ACM Digital Library.
If you are considering submitting to the workshop and have questions regarding the workshop scope or need further information, please do not hesitate to contact the organizers at oddv5.0 (at) gmail.com.
ORGANIZERS
---------------------------
Leman Akoglu (Carnegie Mellon University)
Evgeny Burnaev (Skolkovo Institute of Science and Technology)
Charu Aggarwal (IBM Research)
Christos Faloutsos (Carnegie Mellon University)
CONTACT us at:
oddv5.0 (at) gmail.com