The paper introduces Ra‑NEM, a method that optimizes the area under insertion and deletion curves to improve the faithfulness of feature importance attributions in machine learning models. By deriving an objective function from faithfulness and approximating its gradient, the authors link insertion curves to top‑k feature selection, enabling a loss function that measures attribution quality. Ra‑NEM, integrated with the neural explanation mask framework, works with any differentiable model, yielding accurate, robust, and fast attributions that outperform existing algorithms on multiple XAI metrics.
By Bj{\o}rn Leth M{\o}ller, Bulat Ibragimov, Christian Igel
The paper introduces adVersarial Parameter Decomposition (VPD), a method that splits a language model’s parameters into simple subcomponents, each responsible for a small part of the model’s algorithm. VPD optimizes these decompositions so that the model’s input‑output behavior remains intact even when many subcomponents are removed, including adversarially chosen ones. This approach enables a new form of circuit analysis by tracing how sequences of parameter subcomponents interact to produce outputs for specific inputs.
By Lucius Bushnaq, Dan Braun, Oliver Clive-Griffin, Bart Bussmann, Nathan Hu, Michael Ivanitskiy, Linda Linsefors, Lee Sharkey
arXiv:2311. 02960v5 Announce Type: replace Abstract: Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data.
By Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu
arXiv:2609.06862v1 Announce Type: new
Abstract: Superposition refers to neural networks representing more features than they have dimensions. It offers a possible explanation for polysemantic neurons...
By Dai Shi, Xiaoyu Li, Andi Han, Jos\'e Miguel Hern\'andez-Lobato
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
arXiv:2411. 05698v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification.
By Antonio De Santis, Riccardo Campi, Matteo Bianchi, Marco Brambilla
arXiv:2608. 12299v1 Announce Type: cross Abstract: Class activation mapping (CAM) is one of the most widely used visual explanation families in explainable artificial intelligence.
By AmirHossein Eshghi, Hamid Saadatfar, Seyyed Ali Hoseini, AmirMohsen Eshghi, Siavash Arjomand Bigdel
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:2607. 27463v1 Announce Type: new Abstract: Dimensionality Reduction (DR) is a fundamental tool for high-dimensional data exploration, reducing the complexity of latent spaces of machine learning models, and assisting in the explanation of complex opaque models.
By Lucas Greff Meneses, Evandro S. Ortigossa, Claudio Silva, Luis Gustavo Nonato
arXiv:2610.15299v1 Announce Type: cross
Abstract: Misclassification is a critical problem in many machine learning applications. Since even the classifier models with high accuracy (e.g., > 95%) stil...
By Truong X. Tran, Ramazan S. Aygun
arXiv:2607. 22979v1 Announce Type: cross Abstract: Deep neural networks have been widely used in many applications (e.
By Anand Singh, Luke Pennella, Eshan Kabir, Xiaoxi Shen
arXiv:2606. 00557v1 Announce Type: new Abstract: To understand how a neural network (NN) functions and makes predictions, it has become increasingly clear that analyzing only the input domain is insufficient -- one must also examine its internal inference mechanisms to capture the complete picture.
By Ping Xiong, Thomas Schnake, Gr\'egoire Montavon, Klaus-Robert M\"uller, Shinichi Nakajima