mlsanityData to 7 Oct 2026

MSS-PAE: Saving Autoencoder-based Outlier Detection from Unexpected Reconstruction

arXiv 2304.00709 ↗First posted 3 Apr 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

AutoEncoders (AEs) are commonly used for machine learning tasks due to their intrinsic learning ability. This unique characteristic can be capitalized for Outlier Detection (OD). However conventional AE-based methods face the issue of overconfident decisions and unexpected reconstruction results of outliers, limiting their performance in OD. To mitigate these issues, the Mean Squared Error (MSE) and Negative Logarithmic Likelihood (NLL) were firstly analyzed, and the importance of incorporating aleatoric uncertainty to AE-based OD was elucidated. Then the Weighted Negative Logarithmic Likelihood (WNLL) was proposed to adjust for the effect of uncertainty for different OD scenarios. Moreover, the Mean-Shift Scoring (MSS) method was proposed to utilize the local relationship of data to reduce the issue of false inliers caused by AE. Experiments on 32 real-world OD datasets proved the effectiveness of the proposed methods. The combination of WNLL and MSS achieved 41% relative performance improvement compared to the best baseline. In addition, MSS improved the detection performance of multiple AE-based outlier detectors by an average of 20%. The proposed methods have the potential to advance AE's development in OD.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 87 references that are in the map. First posted on arXiv 3 Apr 2023.

Builds on

24 of 87 references.

References · 24

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  4. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  5. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  6. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  7. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  8. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  9. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  10. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  11. 2019PyOD: A Python Toolbox for Scalable Outlier Detectioncited by 221
  12. 2022ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functionscited by 153
12 more
  1. 2018Uncertainty in Neural Networks: Approximately Bayesian Ensemblingcited by 94
  2. 2022Deep Isolation Forest for Anomaly Detectioncited by 90
  3. 2019Stochastic gradient Markov chain Monte Carlocited by 56
  4. 2020Anomaly Detection With Conditional Variational Autoencoderscited by 46
  5. 2020Uncertainty-Aware Deep Classifiers using Generative Modelscited by 41
  6. 2019Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detectioncited by 35
  7. 2019Robust Subspace Recovery Layer for Unsupervised Anomaly Detectioncited by 31
  8. 2018Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoderscited by 26
  9. 2020Memory Augmented Generative Adversarial Networks for Anomaly Detectioncited by 12
  10. 2020Interpreting Rate-Distortion of Variational Autoencoder and Using Model Uncertainty for Anomaly Detectioncited by 10
  11. 2021Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution Detectioncited by 4
  12. 2022Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detectioncited by 4

Built on by

Not cited yet.