Unsupervised Incremental Learning with Dual Concept Drift Detection for Identifying Anomalous Sequences

Abstract

In the contemporary digital landscape, the continuous generation of extensive streaming data across diverse domains has become pervasive. Yet, a significant portion of this data remains unlabeled, posing a challenge in identifying infrequent events such as anomalies. This challenge is further amplified in non-stationary environments, where the performance of models can degrade over time due to concept drift. To address these challenges, this paper introduces a new method referred to as VAE4AS (Variational Autoencoder for Anomalous Sequences). VAE4AS integrates incremental learning with dual drift detection mechanisms, employing both a statistical test and a distance-based test. The anomaly detection is facilitated by a Variational Autoencoder. To gauge the effectiveness of VAE4AS, a comprehensive experimental study is conducted using real-world and synthetic datasets characterized by anomalous rates below 10\% and recurrent drift. The results show that the proposed method surpasses both robust baselines and state-of-the-art techniques, providing compelling evidence for their efficacy in effectively addressing some of the challenges associated with anomalous sequence detection in non-stationary streaming data.

arXiv commentsubmitted to IJCNN2024,under review

References in corpus (8)

• Auto-Encoding Variational Bayes
• Deep Learning for Anomaly Detection: A Survey
• Random Partitioning Forest for Point-Wise and Collective Anomaly Detection -- Application to Intrusion Detection
• Online Learning With Adaptive Rebalancing in Nonstationary Environments
• Nonstationary data stream classification with online active learning and siamese neural networks
• Autoencoder-based Anomaly Detection in Streaming Data with Incremental Learning and Concept Drift Adaptation
• Data augmentation on-the-fly and active learning in data stream classification
• A Hybrid Active-Passive Approach to Imbalanced Nonstationary Data Stream Classification

Cited by in corpus (2)

• SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networks
• Online Detection of Water Contamination Under Concept Drift