Deep Reinforcement Learning for Unknown Anomaly Detection

by   Guansong Pang, et al.

We address a critical yet largely unsolved anomaly detection problem, in which we aim to learn detection models from a small set of partially labeled anomalies and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either proceed unsupervised with the unlabeled data, or exclusively fit the limited anomaly examples that often do not span the entire set of anomalies. We propose here instead a deep reinforcement-learning-based approach that actively seeks novel classes of anomaly that lie beyond the scope of the labeled training data. This approach learns to balance exploiting its existing data model against exploring for new classes of anomaly. It is thus able to exploit the labeled anomaly data to improve detection accuracy, without limiting the set of anomalies sought to those given anomaly examples. This is of significant practical benefit, as anomalies are inevitably unpredictable in form and often expensive to miss. Extensive experiments on 48 real-world datasets show that our approach significantly outperforms five state-of-the-art competing methods.


page 1

page 2

page 3

page 4


Weakly-supervised Deep Anomaly Detection with Pairwise Relation Learning

This paper studies a rarely explored but critical anomaly detection prob...

A Simple Unified Framework for Anomaly Detection in Deep Reinforcement Learning

Abnormal states in deep reinforcement learning (RL) are states that are ...

Deep Anomaly Detection and Search via Reinforcement Learning

Semi-supervised Anomaly Detection (AD) is a kind of data mining task whi...

LogDP: Combining Dependency and Proximity for Log-based Anomaly Detection

Log analysis is an important technique that engineers use for troublesho...

Few-shot Deep Representation Learning based on Information Bottleneck Principle

In a standard anomaly detection problem, a detection model is trained in...

Isconna: Streaming Anomaly Detection with Frequency and Patterns

An edge stream is a common form of presentation of dynamic networks. It ...

Learning Acceptance Regions for Many Classes with Anomaly Detection

Set-valued classification, a new classification paradigm that aims to id...

Code Repositories


Paper Implementation

view repo