August 12, 2025ACM Transactions on Knowledge Discovery from Data0 citations

Memory Augmented Autoencoder with Contrastive Learning for Anomaly Detection

MCAKE: Memory Augmented Autoencoder with Contrastive Learning for Unsupervised Anomaly Detection

View Full Paper

Ask AI

Bookmark

Authors

CWChengsen Wang QQQi Qi JWJinming Wu

Discussion

Member takes

Overview

Proposed model improves unsupervised anomaly detection by enhancing memory networks, highlighting deviation scores, and utilizing a bivariate detection criterion.

Key Points

MCAKE enhances unsupervised anomaly detection by using memory-augmented contrastive learning.
The method employs a unique memory updating process to retain normal prototypes for better reconstruction.
A bivariate detection criterion is introduced to compute anomaly scores in both input and latent spaces.
Extensive testing on 50 datasets shows MCAKE achieves a 2% improvement over existing state-of-the-art models.

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/689e03e9d61984b91e13d260 https://doi.org/10.1145/3759460

View Full Paper

Ask AI

Bookmark

August 12, 2025ACM Transactions on Knowledge Discovery from Data0 citations

Memory Augmented Autoencoder with Contrastive Learning for Anomaly Detection

MCAKE: Memory Augmented Autoencoder with Contrastive Learning for Unsupervised Anomaly Detection

View Full Paper

Ask AI

Bookmark

Authors

CWChengsen Wang QQQi Qi JWJinming Wu

Discussion

Member takes

Overview

Proposed model improves unsupervised anomaly detection by enhancing memory networks, highlighting deviation scores, and utilizing a bivariate detection criterion.

Key Points

MCAKE enhances unsupervised anomaly detection by using memory-augmented contrastive learning.
The method employs a unique memory updating process to retain normal prototypes for better reconstruction.
A bivariate detection criterion is introduced to compute anomaly scores in both input and latent spaces.
Extensive testing on 50 datasets shows MCAKE achieves a 2% improvement over existing state-of-the-art models.

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/689e03e9d61984b91e13d260 https://doi.org/10.1145/3759460

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark