# Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learning

arXiv: https://arxiv.org/abs/2110.10038 · HTML: https://mlsanity.com/paper/2110.10038/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 85 references that are in the map.
- First posted on arXiv 19 Oct 2021.

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Deep Learning for Anomaly Detection: A Review](https://mlsanity.com/paper/2007.02500/) (2020)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Explainable Deep One-Class Classification](https://mlsanity.com/paper/2007.01760/) (2020)
- [Uncertainty in Neural Networks: Approximately Bayesian Ensembling](https://mlsanity.com/paper/1810.05546/) (2018)
- [Quality of Uncertainty Quantification for Bayesian Neural Network Inference](https://mlsanity.com/paper/1906.09686/) (2019)
- [Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series](https://mlsanity.com/paper/2010.05073/) (2020)
- [GEE: A Gradient-based Explainable Variational Autoencoder for Network Anomaly Detection](https://mlsanity.com/paper/1903.06661/) (2019)
- [Explaining Anomalies Detected by Autoencoders Using SHAP](https://mlsanity.com/paper/1903.02407/) (2019)
- [Process Outcome Prediction: CNN vs. LSTM (with Attention)](https://mlsanity.com/paper/2104.06934/) (2021)
- [Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics -- A Comprehensive Review](https://mlsanity.com/paper/1901.08247/) (2019)
- [Bayesian Autoencoders for Drift Detection in Industrial Environments](https://mlsanity.com/paper/2107.13249/) (2021)
- [Instance Selection Improves Geometric Mean Accuracy: A Study on Imbalanced Data Classification](https://mlsanity.com/paper/1804.07155/) (2018)
- [Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution Detection](https://mlsanity.com/paper/2107.13304/) (2021)
- [Multi Agent System for Machine Learning Under Uncertainty in Cyber Physical Manufacturing System](https://mlsanity.com/paper/2107.13252/) (2021)

## Abstract (arXiv)

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.