VIAL-AD: Visual Interactive Labelling for Anomaly Detection - An Approach and Open Research Questions

In anomaly detection problems the available data is often not or not fully labelled. This leads to results that are usually significantly worse than in balanced classification problems. In this short paper VIAL-AD is proposed, which addresses this problem with a sequence of unsupervised, semi-supervised and supervised machine learning models allowing a user to interactively label data points. This allows to move towards supervised anomaly detection, starting with unlabelled data. The approach is introduced and identified open research questions are discussed.

[1]  Bartosz Krawczyk,et al.  Learning from imbalanced data: open challenges and future directions , 2016, Progress in Artificial Intelligence.

[2]  Ammar Belatreche,et al.  An experimental evaluation of novelty detection methods , 2014, Neurocomputing.

[3]  Carlos Eduardo Scheidegger,et al.  DimReader: Axis lines that explain non-linear projections , 2017, IEEE Transactions on Visualization and Computer Graphics.

[4]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[5]  Antti Oulasvirta,et al.  Towards Perceptual Optimization of the Visual Design of Scatterplots , 2017, IEEE Transactions on Visualization and Computer Graphics.

[6]  David M. J. Tax,et al.  One-class classification , 2001 .

[7]  Daniel A. Keim,et al.  What you see is what you can change: Human-centered machine learning by interactive visualization , 2017, Neurocomputing.

[8]  Tamara Munzner,et al.  A Taxonomy of Visual Cluster Separation Factors , 2012, Comput. Graph. Forum.

[9]  Andreas Theissler.  Detecting anomalies in multivariate time series from automotive systems , 2013 .

[10]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[11]  Marius Kloft,et al.  Toward Supervised Anomaly Detection , 2014, J. Artif. Intell. Res..

[12]  Chris North,et al.  Semantic Interaction for Sensemaking: Inferring Analytical Reasoning for Model Steering , 2012, IEEE Transactions on Visualization and Computer Graphics.

[13]  Marco Hutter,et al.  Comparing Visual-Interactive Labeling with Active Learning: An Experimental Study , 2018, IEEE Transactions on Visualization and Computer Graphics.

[14]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[15]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[16]  Andreas Holzinger,et al.  Interactive machine learning: experimental evidence for the human in the algorithmic loop , 2018, Applied Intelligence.

[17]  Jürgen Bernard,et al.  VIAL: a unified process for visual interactive labeling , 2018, The Visual Computer.

[18]  Andreas Theissler,et al.  Detecting known and unknown faults in automotive systems using ensemble-based anomaly detection , 2017, Knowl. Based Syst..

[19]  Stefan Holzer,et al.  VisCoDeR: A tool for visually comparing dimensionality reduction algorithms , 2018, ESANN.

[20]  Daniel A. Keim,et al.  Visual Interaction with Dimensionality Reduction: A Structured Literature Analysis , 2017, IEEE Transactions on Visualization and Computer Graphics.

[21]  Chris North,et al.  Towards a Systematic Combination of Dimension Reduction and Clustering in Visual Analytics , 2018, IEEE Transactions on Visualization and Computer Graphics.

[22]  Klemens Böhm,et al.  Validating one-class active learning with user studies – A prototype and open challenges , 2019 .

[23]  Dieter W. Fellner,et al.  Combining Cluster and Outlier Analysis with Visual Analytics , 2017, EuroVA@EuroVis.

[24]  Andreas Theissler,et al.  Multi-class novelty detection in diagnostic trouble codes from repair shops , 2017, 2017 IEEE 15th International Conference on Industrial Informatics (INDIN).