mlsanityData to 7 Oct 2026

Hidden Monotonicity: Explaining Deep Neural Networks via their DC Decomposition

arXiv 2601.07700 ↗First posted 12 Jan 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

It has been demonstrated in various contexts that monotonicity leads to better explainability in neural networks. However, not every function can be well approximated by a monotone neural network. We demonstrate that monotonicity can still be used in two ways to boost explainability. First, we use an adaptation of the decomposition of a trained ReLU network into two monotone and convex parts, thereby overcoming numerical obstacles from an inherent blowup of the weights in this procedure. Our proposed saliency methods - SplitCAM and SplitLRP - improve on state of the art results on both VGG16 and Resnet18 networks on ImageNet-S across all Quantus saliency metric categories. Second, we exhibit that training a model as the difference between two monotone neural networks results in a system with strong self-explainability properties.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 66 references that are in the map. First posted on arXiv 12 Jan 2026.

Builds on

44 of 66 references.

References · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  8. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  9. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  10. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  11. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  12. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
32 more
  1. 2018Sanity Checks for Saliency Mapscited by 1,149
  2. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  3. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  4. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  5. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  6. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  7. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  8. 2016Input Convex Neural Networkscited by 407
  9. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  10. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  11. 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
  12. 2016Understanding Deep Neural Networks with Rectified Linear Unitscited by 253
  13. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  14. 2021Towards Robust Vision Transformercited by 137
  15. 2018Tropical Geometry of Deep Neural Networkscited by 92
  16. 2019Towards Best Practice in Explaining Neural Network Decisions with LRPcited by 70
  17. 2020Certified Monotonic Neural Networkscited by 51
  18. 2022Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysiscited by 38
  19. 2023Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopescited by 36
  20. 2020Counterexample-Guided Learning of Monotonic Neural Networkscited by 34
  21. 2018Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Modelscited by 24
  22. 2024The Real Tropical Geometry of Neural Networkscited by 23
  23. 2022Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanationscited by 22
  24. 2020Deontological Ethics By Monotonicity Shape Constraintscited by 16
  25. 2020The Curious Case of Convex Neural Networkscited by 16
  26. 2020Piecewise Linear Regression via a Difference of Convex Functionscited by 14
  27. 2020The Clever Hans Effect in Anomaly Detectioncited by 13
  28. 2018Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Datacited by 9
  29. 2022Explaining Image Classifiers with Multiscale Directional Image Representationcited by 7
  30. 2023Representing Piecewise Linear Functions by Functions with Small Aritycited by 7
  31. 2021CDiNN -Convex Difference Neural Networkscited by 6
  32. 2021Novel convex decomposition of piecewise affine functionscited by 4

Built on by

Not cited yet.