# A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines

arXiv: https://arxiv.org/abs/2111.07379 · HTML: https://mlsanity.com/paper/2111.07379/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 14 Nov 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations](https://mlsanity.com/paper/2012.03058/) (2020)
- [GLocalX -- From Local to Global Explanations of Black Box AI Models](https://mlsanity.com/paper/2101.07685/) (2021)
- [IROF: a low resource evaluation metric for explanation methods](https://mlsanity.com/paper/2003.08747/) (2020)
- [On Baselines for Local Feature Attributions](https://mlsanity.com/paper/2101.00905/) (2021)
- [Unsupervised Ensemble Learning with Dependent Classifiers](https://mlsanity.com/paper/1510.05830/) (2015)
- [A Deep Learning Approach to Unsupervised Ensemble Learning](https://mlsanity.com/paper/1602.02285/) (2016)
- [Aggregating explanation methods for stable and robust explainability](https://mlsanity.com/paper/1903.00519/) (2019)
- [A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees](https://mlsanity.com/paper/1809.09703/) (2018)
- [Restricted Boltzmann Machines for Robust and Fast Latent Truth Discovery](https://mlsanity.com/paper/1801.00283/) (2017)

## Built on by (most cited first, 2 of 2)

- [Fidelity of Ensemble Aggregation for Saliency Map Explanations using Bayesian Optimization Techniques](https://mlsanity.com/paper/2207.01565/) (2022)
- [Relational Local Explanations](https://mlsanity.com/paper/2212.12374/) (2022)

## Abstract (arXiv)

Understanding the results of deep neural networks is an essential step towards wider acceptance of deep learning algorithms. Many approaches address the issue of interpreting artificial neural networks, but often provide divergent explanations. Moreover, different hyperparameters of an explanatory method can lead to conflicting interpretations. In this paper, we propose a technique for aggregating the feature attributions of different explanatory algorithms using Restricted Boltzmann Machines (RBMs) to achieve a more reliable and robust interpretation of deep neural networks. Several challenging experiments on real-world datasets show that the proposed RBM method outperforms popular feature attribution methods and basic ensemble techniques.