A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines
Not on the map. Why?
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 14 Nov 2021.
Builds on
25 of 44 references.
References · 25
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2018Sanity Checks for Saliency Mapscited by 1,149
- 2017SmoothGrad: removing noise by adding noisecited by 1,097
- 2014Striving for Simplicity: The All Convolutional Netcited by 983
- 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
- 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
13 more
- 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
- 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
- 2020A Survey on Neural Network Interpretabilitycited by 291
- 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
- 2020BayLIME: Bayesian Local Interpretable Model-Agnostic Explanationscited by 51
- 2021GLocalX -- From Local to Global Explanations of Black Box AI Modelscited by 48
- 2020IROF: a low resource evaluation metric for explanation methodscited by 45
- 2021On Baselines for Local Feature Attributionscited by 29
- 2015Unsupervised Ensemble Learning with Dependent Classifierscited by 19
- 2016A Deep Learning Approach to Unsupervised Ensemble Learningcited by 12
- 2019Aggregating explanation methods for stable and robust explainabilitycited by 9
- 2018A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Treescited by 5
- 2017Restricted Boltzmann Machines for Robust and Fast Latent Truth Discoverycited by 1
Built on by
Citing papers per year: 2022: 2.
2 papers.