Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection

Abstract

Learning expressive low-dimensional representations of ultrahigh-dimensional data, e.g., data with thousands/millions of features, has been a major way to enable learning methods to address the curse of dimensionality. However, existing unsupervised representation learning methods mainly focus on preserving the data regularity information and learning the representations independently of subsequent outlier detection methods, which can result in suboptimal and unstable performance of detecting irregularities (i.e., outliers). This paper introduces a ranking model-based framework, called RAMODO, to address this issue. RAMODO unifies representation learning and outlier detection to learn low-dimensional representations that are tailored for a state-of-the-art outlier detection approach - the random distance-based approach. This customized learning yields more optimal and stable representations for the targeted outlier detectors. Additionally, RAMODO can leverage little labeled data as prior knowledge to learn more expressive and application-relevant representations. We instantiate RAMODO to an efficient method called REPEN to demonstrate the performance of RAMODO. Extensive empirical results on eight real-world ultrahigh dimensional data sets show that REPEN (i) enables a random distance-based detector to obtain significantly better AUC performance and two orders of magnitude speedup; (ii) performs substantially better and more stably than four state-of-the-art representation learning methods; and (iii) leverages less than 1% labeled data to achieve up to 32% AUC improvement.

10 pages, 4 figures, 3 tables. To appear in the proceedings of KDD18, Long presentation (oral)

References in corpus (3)

• ADADELTA: An Adaptive Learning Rate Method
• Winner-Take-All Autoencoders
• Less is More: Building Selective Anomaly Ensembles

Cited by in corpus (31)

• Deep Learning for Anomaly Detection: A Review
• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
• Deep Isolation Forest for Anomaly Detection
• Feature Encoding with AutoEncoders for Weakly-supervised Anomaly Detection
• Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection
• DTAAD: Dual Tcn-Attention Networks for Anomaly Detection in Multivariate Time Series Data
• Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data
• Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation
• Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Stream
• Explainable Deep Few-shot Anomaly Detection with Deviation Networks
• Deep Weakly-supervised Anomaly Detection
• Outlier Detection in High Dimensional Data
• RLAD: Time Series Anomaly Detection through Reinforcement Learning and Active Learning
• Anomaly Detection with Score Distribution Discrimination
• Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning
• Outlier detection in mixed-attribute data: a semi-supervised approach with fuzzy approximations and relative entropy
• Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning
• Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators
• Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy
• Deep Anomaly Detection with Deviation Networks
• A Simple Framework for Uncertainty in Contrastive Learning
• Outlier Detection Ensemble with Embedded Feature Selection
• R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
• Unsupervised Representation Learning by Predicting Random Distances
• Multi-representations Space Separation based Graph-level Anomaly-aware Detection
• Anomaly Detection by Recombining Gated Unsupervised Experts
• Label-Informed Outlier Detection Based on Granule Density
• Enhancing Unsupervised Anomaly Detection with Score-Guided Network
• Algorithmic Frameworks for the Detection of High Density Anomalies
• IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation
• Reconstruct Anomaly to Normal: Adversarial Learned and Latent Vector-constrained Autoencoder for Time-series Anomaly Detection