mlsanityData to 14 Oct 2026

LEURN: Learning Explainable Univariate Rules with Neural Networks

arXiv 2303.14937 ↗First posted 27 Mar 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose LEURN: a neural network architecture that learns univariate decision rules. LEURN is a white-box algorithm that results into univariate trees and makes explainable decisions in every stage. In each layer, LEURN finds a set of univariate rules based on an embedding of the previously checked rules and their corresponding responses. Both rule finding and final decision mechanisms are weighted linear combinations of these embeddings, hence contribution of all rules are clearly formulated and explainable. LEURN can select features, extract feature importance, provide semantic similarity between a pair of samples, be used in a generative manner and can give a confidence score. Thanks to a smoothness parameter, LEURN can also controllably behave like decision trees or vanilla neural networks. Besides these advantages, LEURN achieves comparable performance to state-of-the-art methods across 30 tabular datasets for classification and regression problems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 43 of its 58 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

43 of 58 references.

References · 43

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  7. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  8. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  9. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  10. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  11. 2021Tabular Data: Deep Learning is Not All You Needcited by 535
  12. 2014OpenML: networked science in machine learningcited by 526
31 more
  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  2. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 409
  3. 2016Top-down Neural Attention by Excitation Backpropcited by 321
  4. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
  5. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 319
  6. 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
  7. 2018CatBoost: gradient boosting with categorical features supportcited by 208
  8. 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 203
  9. 2022Why do tree-based models still outperform deep learning on tabular data?cited by 199
  10. 2020Eigen-CAM: Class Activation Map using Principal Componentscited by 189
  11. 2022On Embeddings for Numerical Features in Tabular Deep Learningcited by 186
  12. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 156
  13. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  14. 2017Convolutional Networks with Adaptive Inference Graphscited by 148
  15. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  16. 2018Tropical Geometry of Deep Neural Networkscited by 95
  17. 2020Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networkscited by 79
  18. 2018Deep Neural Decision Treescited by 72
  19. 2017Beyond Sparsity: Tree Regularization of Deep Models for Interpretabilitycited by 68
  20. 2018Deep Feature Factorization For Concept Discoverycited by 64
  21. 2022Neural Basis Models for Interpretabilitycited by 56
  22. 2016Network of Experts for Large-Scale Image Categorizationcited by 54
  23. 2022Transfer Learning with Deep Tabular Modelscited by 52
  24. 2020NBDT: Neural-Backed Decision Treescited by 46
  25. 2022Revisiting Pretraining Objectives for Tabular Deep Learningcited by 43
  26. 2017Deciding How to Decide: Dynamic Routing in Artificial Neural Networkscited by 33
  27. 2020Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplificationcited by 32
  28. 2017Neural Decision Treescited by 17
  29. 2022Neural Networks are Decision Treescited by 17
  30. 2015Blockout: Dynamic Model Selection for Hierarchical Deep Networkscited by 11
  31. 2020Towards Interpretable ANNs: An Exact Transformation to Multi-Class Multivariate Decision Treescited by 6

Built on by

Not cited yet.