Generative Subspace Adversarial Active Learning for Outlier Detection in Multiple Views of High-dimensional Tabular Data

Jose Cribeiro-Ramallo, Vadim Arzamasov, Federico Matteucci, Denis Wambold, Klemens Böhm

Keywords: Outlier Detection, One-class classification, GAN, Active Learning, Tabular data

TL;DR: We built a generative method for outlier detection in subspaces of tabular data. Our results show how our method greatly outperforms competitors in detecting fine-grainned anomalies in the subsapace.

Abstract: Outlier detection in high-dimensional tabular data is an important task in data mining, essential for many downstream tasks and applications. Existing unsupervised outlier detection algorithms face one or more problems, including inlier assumption (IA), curse of dimensionality (CD), and multiple views (MV). To address these issues, we introduce Generative Subspace Adversarial Active Learning (GSAAL), a novel approach that uses a Generative Adversarial Network with multiple adversaries. These adversaries learn the marginal class probability functions over different data subspaces, while a single generator in the full space models the entire distribution of the inlier class. GSAAL is specifically designed to address the MV limitation while also handling the IA and CD, being the only method to do so. We provide a mathematical formulation of MV, convergence guarantees for the discriminators, and scalability results for GSAAL. Our extensive experiments demonstrate the effectiveness and scalability of GSAAL, highlighting its superior performance compared to other popular OD methods, especially in MV scenarios.

Primary Area: Deep learning architectures

Submission Number: 1682