Attention-like feature explanation for tabular data
Not on the map. Why?
Abstract (arXiv)
A new method for local and global explanation of the machine learning black-box model predictions by tabular data is proposed. It is implemented as a system called AFEX (Attention-like Feature EXplanation) and consisting of two main parts. The first part is a set of the one-feature neural subnetworks which aim to get a specific representation for every feature in the form of a basis of shape functions. The subnetworks use shortcut connections with trainable parameters to improve the network performance. The second part of AFEX produces shape functions of features as the weighted sum of the basis shape functions where weights are computed by using an attention-like mechanism. AFEX identifies pairwise interactions between features based on pairwise multiplications of shape functions corresponding to different features. A modification of AFEX with incorporating an additional surrogate model which approximates the black-box model is proposed. AFEX is trained end-to-end on a whole dataset only once such that it does not require to train neural networks again in the explanation stage. Numerical experiments with synthetic and real data illustrate AFEX.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 54 of its 76 references that are in the map. First posted on arXiv 10 Aug 2021.
Builds on
54 of 76 references.
References · 54
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 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
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
- 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
- 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
- 2019Attention is not Explanationcited by 916
- 2014Neural Turing Machinescited by 630
- 2019Attention is not not Explanationcited by 629
38 more
- 2021A Survey of Transformerscited by 399
- 2019Is Attention Interpretable?cited by 387
- 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
- 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
- 2020A Survey on Neural Network Interpretabilitycited by 291
- 2019InterpretML: A Unified Framework for Machine Learning Interpretabilitycited by 243
- 2018Techniques for Interpretable Machine Learningcited by 237
- 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
- 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 200
- 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
- 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
- 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
- 2019An Attentive Survey of Attention Modelscited by 123
- 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
- 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
- 2021Dive into Deep Learningcited by 111
- 2020Principles and Practice of Explainable Machine Learningcited by 99
- 2018Grounding Visual Explanationscited by 92
- 2020Explaining the Explainer: A First Theoretical Analysis of LIMEcited by 89
- 2021NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learningcited by 88
- 2020GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactionscited by 82
- 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
- 2021Personalized Transformer for Explainable Recommendationcited by 58
- 2020How Interpretable and Trustworthy are GAMs?cited by 44
- 2019ALIME: Autoencoder Based Approach for Local Interpretabilitycited by 41
- 2021Shapley Explanation Networkscited by 41
- 2020SurvLIME: A method for explaining machine learning survival modelscited by 34
- 2021On Locality of Local Explanation Modelscited by 25
- 2021Accuracy, Interpretability, and Differential Privacy via Explainable Boostingcited by 24
- 2019Enriching Visual with Verbal Explanations for Relational Concepts -- Combining LIME with Alephcited by 23
- 2021SHAFF: Fast and consistent SHApley eFfect estimates via random Forestscited by 22
- 2020Feature Importance Estimation with Self-Attention Networkscited by 21
- 2021SurvNAM: The machine learning survival model explanationcited by 16
- 2020Interpretable Machine Learning with an Ensemble of Gradient Boosting Machinescited by 14
- 2019Explanation vs Attention: A Two-Player Game to Obtain Attention for VQAcited by 12
- 2019c-Eval: A Unified Metric to Evaluate Feature-based Explanations via Perturbationcited by 7
- 2020Adaptive Explainable Neural Networks (AxNNs)cited by 7
- 2020X-SHAP: towards multiplicative explainability of Machine Learningcited by 5
50 most cited of 54 All 54 (JSON)
Built on by
Citing papers per year: 2022: 1; 2023: 2.
3 papers.