Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learning
This paper aims to improve the explainability of Autoencoder's (AE) predictions by proposing two explanation methods based on the mean and epistemic uncertainty of log-likelihood estimate, which naturally arise from the probabilistic formulation of the AE called Bayesian Autoencoders (BAE). To quantitatively evaluate the performance of explanation methods, we test them in sensor network applications, and propose three metrics based on covariate shift of sensors : (1) G-mean of Spearman drift coefficients, (2) G-mean of sensitivity-specificity of explanation ranking and (3) sensor explanation quality index (SEQI) which combines the two aforementioned metrics. Surprisingly, we find that explanations of BAE's predictions suffer from high correlation resulting in misleading explanations. To alleviate this, a "Coalitional BAE" is proposed, which is inspired by agent-based system theory. Our comprehensive experiments on publicly available condition monitoring datasets demonstrate the improved quality of explanations using the Coalitional BAE.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningSpecificityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version
Time series data occurs widely, and outlier detection is a fundamental problem in data mining, which has numerous applications. Existing autoencoder-based approaches deliver state-of-the-art performance on challenging re…
Outlier DetectionTime SeriesTime Series AnalysisBayesian Autoencoders for Drift Detection in Industrial Environments
Autoencoders are unsupervised models which have been used for detecting anomalies in multi-sensor environments. A typical use includes training a predictive model with data from sensors operating under normal conditions …
Drift DetectionBayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection
Despite numerous studies of deep autoencoders (AEs) for unsupervised anomaly detection, AEs still lack a way to express uncertainty in their predictions, crucial for ensuring safe and trustworthy machine learning systems…
Anomaly DetectionUncertainty QuantificationUnsupervised Anomaly DetectionUnsupervised Features Ranking via Coalitional Game Theory for Categorical Data
Not all real-world data are labeled, and when labels are not available, it is often costly to obtain them. Moreover, as many algorithms suffer from the curse of dimensionality, reducing the features in the data to a smal…
Anomaly DetectionFeature Importancefeature selectionQuantization-Based Regularization for Autoencoders
Autoencoders and their variations provide unsupervised models for learning low-dimensional representations for downstream tasks. Without proper regularization, autoencoder models are susceptible to the overfitting proble…
ClusteringDecoderDenoisingQuantization