ARCADe: A Rapid Continual Anomaly Detector

Abstract

Although continual learning and anomaly detection have separately been well-studied in previous works, their intersection remains rather unexplored. The present work addresses a learning scenario where a model has to incrementally learn a sequence of anomaly detection tasks, i.e. tasks from which only examples from the normal (majority) class are available for training. We define this novel learning problem of continual anomaly detection (CAD) and formulate it as a meta-learning problem. Moreover, we propose A Rapid Continual Anomaly Detector (ARCADe), an approach to train neural networks to be robust against the major challenges of this new learning problem, namely catastrophic forgetting and overfitting to the majority class. The results of our experiments on three datasets show that, in the CAD problem setting, ARCADe substantially outperforms baselines from the continual learning and anomaly detection literature. Finally, we provide deeper insights into the learning strategy yielded by the proposed meta-learning algorithm.

arXiv commentAccepted at ICPR 2020

References in corpus (19)

• Overcoming catastrophic forgetting in neural networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Prioritized Experience Replay
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• Continual Learning Through Synaptic Intelligence
• Matching Networks for One Shot Learning
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• One-Class Classification: Taxonomy of Study and Review of Techniques
• Gradient Episodic Memory for Continual Learning
• Overcoming Catastrophic Forgetting by Incremental Moment Matching
• Meta-learning with differentiable closed-form solvers
• Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm
• Learning to Continually Learn
• Task Agnostic Continual Learning via Meta Learning
• Adversarial Meta-Learning
• Variational Prototype Replays for Continual Learning
• Meta-learnt priors slow down catastrophic forgetting in neural networks