The paper introduces a control‑variable framework for deep neural networks to mitigate omitted variable bias, particularly shortcut learning where covariates like demographics influence predictions. It refits the final layer of a pre‑trained network using cross‑fitting with ridge penalisation, orthogonalises covariate effects, and marginalises predictions over covariate distributions to achieve unbiased, interpretable results. Experiments on simulated images and neuroimaging data show consistent estimation of true effects and performance close to models trained on unconfounded data.
By Manuel Pfeuffer, Roshan Prakash Rane, Kerstin Ritter, Sonja Greven
arXiv:2310.16295v2 Announce Type: replace-cross
Abstract: Neural network have achieved remarkable successes in many scientific fields. However, the interpretability of the neural network model is sti...
By Zhimin Li, Shusen Liu, Kailkhura Bhavya, Peer-Timo Bremer, Valerio Pascucci
NObSP (Nonlinear Oblique Subspace Projections) is a framework that decomposes neural network predictions into explicit per‑feature contribution functions and an interaction residual, leveraging the linear final layer and oblique projections to avoid double counting when feature subspaces overlap. It connects to functional ANOVA and the Kolmogorov‑Arnold representation theorem, and introduces an efficient partial regression algorithm for out‑of‑sample evaluation. For convolutional networks, NObSP‑CAM generates class activation maps without backward passes after a single calibration, and experiments on tabular and vision datasets show faithfulness comparable to established attribution methods, with high function reproduction scores and improved class purity on TinyImageNet.
By Alexander Caicedo, V\'ictor De La Hoz, Santiago Alf\'erez
The paper introduces ICON decomposition, a method for auditing neural networks by decomposing the variance of intermediate representations into contributions from Independent Canonical Concepts (ICON). Unlike traditional decodability metrics, ICON isolates each concept’s influence while conditioning on all other concepts and the outcome, providing a clearer view of which concepts truly drive predictions. Experiments on simulated data and real-world skin‑cancer and neuroimaging tasks show ICON outperforms seven baseline methods and successfully distinguishes genuine shortcuts from merely correlated features.
By Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer, Marc-Andre Schulz, Nys Tjade Siegel, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sonja Greven, Kerstin Ritter
ICON Decomposition is a new method for explaining deep neural networks by quantifying how much variance each concept explains in a network layer after accounting for all other concepts and the outcome. Unlike previous concept‑based methods that evaluate concepts in isolation, ICON can distinguish genuine model reliance from spurious correlations. Experiments on synthetic data, skin‑lesion, and brain‑imaging models show that ICON recovers concept importance more accurately, isolates truly relied‑upon concepts, and provides sparse explanations validated through retraining and out‑of‑distribution testing.
By Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer, Marc-Andre Schulz, Nys Tjade Siegel, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sonja Greven, Kerstin Ritter
The paper introduces ICON Decomposition, a method for auditing deep neural networks by decomposing layer-wise representations into independent concept contributions. Unlike existing techniques that rely on linear probes or concept activation vectors, ICON quantifies the variance share each concept explains while conditioning on all other concepts and the outcome, allowing comparison across layers and concept types. Experiments on simulated data, skin‑cancer, and neuroimaging models show that ICON more accurately recovers true concept importance and can distinguish learned shortcuts from correlated concepts, as validated by retraining and out‑of‑distribution tests.
By Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer, Marc-Andre Schulz, Nys Tjade Siegel, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sonja Greven, Kerstin Ritter
arXiv:2207. 12877v3 Announce Type: replace Abstract: Motivated by the successes of deep learning, we propose a class of neural network-based discrete choice models, called RUMnets, inspired by the random utility maximization (RUM) framework.
By Ali Aouad, Antoine D\'esir
arXiv:2606. 29951v1 Announce Type: new Abstract: Interpretable Mesomorphic Neural Networks (IMNs) offer a promising framework that combines the predictive power of deep neural networks with the interpretability of linear models.
By Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton, P{\aa}l Halvorsen
arXiv:2503. 10496v2 Announce Type: replace-cross Abstract: Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions.
By Eirik H{\o}yheim, Lars Skaaret-Lund, Solve S{\ae}b{\o}, Aliaksandr Hubin
arXiv:2606. 30953v1 Announce Type: new Abstract: We introduce the Neuro-Bayesian-Symbolic Residual Attention Shallow Network (NBS-RASN), a hybrid neural architecture for explainable cybersecurity risk assessment in open-source ecosystems.
By Nicolaie Popescu-Bodorin, Madeleine Togher
arXiv:2608.26083v2 Announce Type: replace-cross
Abstract: Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Auditing for shortcuts requires testing many...
By Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer, Marc-Andre Schulz, Nys Tjade Siegel, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sonja Greven, Kerstin Ritter
arXiv:2504. 15388v3 Announce Type: replace-cross Abstract: In the context of multivariate nonparametric regression with missing covariates, we propose Pattern Embedded Neural Networks (PENNs), which can be applied in conjunction with any existing imputation technique.
By Tianyi Ma, Tengyao Wang, Richard J. Samworth