.png){kind=icon}
返回
Adaptive Memory Networks With Self-Supervised Learning for Unsupervised Anomaly Detection
.png){kind=icon}
OA
AI
DOI：10.1109/TKDE.2021.3139916.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Unsupervised anomaly detection aims to build models to effectively detect unseen anomalies by only training on the normal data. Although previous reconstruction-based methods have made fruitful progress, their generalization ability is limited due to two critical challenges. First, the training dataset only contains normal patterns, which limits the model generalization ability. Second, the feature representations learned by existing models often lack representativeness which hampers the ability to preserve the diversity of normal patterns. In this paper, we propose a novel approach called Adaptive Memory Network with Self-supervised Learning (AMSL) to address these challenges and enhance the generalization ability in unsupervised anomaly detection. Based on the convolutional autoencoder structure, AMSL incorporates a self-supervised learning module to learn general normal patterns and an adaptive memory fusion module to learn rich feature representations. Experiments on four public multivariate time series datasets demonstrate that AMSL significantly improves the performance compared to other state-of-the-art methods. Specifically, on the largest CAP sleep stage detection dataset with 900 million samples, AMSL outperforms the second-best baseline by 4%+ in both accuracy and F1 score. Apart from the enhanced generalization ability, AMSL is also more robust against input noise.
Keyword:
Unsupervised anomaly detection
time series
self-supervised learning
memory network
期刊
IF:
10.4
论文数:
6.9K
被引数:
3.2W
机构
引用论文
.png){kind=icon}
分享收藏
Electrothermal Model for Power LEDs Based on the Equivalent Resistance Concept for LED Driver Design基于LED驱动器设计的等效电阻概念的功率LED电热模型
PREAI
分享收藏Effects of diazepam on the latency of saccades for luminance and binocular disparity defined stimuli
PREAI
分享收藏分享收藏
查看更多内容