Neural Network Interpretability

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 450% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 203

All topics

The Polytopal Neural Network
Oct 8, 2026A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski +2Neural Network Interpretability Geometric Representation Learning
Technical University of Denmark · UiT The Arctic University of Norway
RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
Oct 8, 2026Ilya Lasy, Nora Yinuo Cai, Kola AyonrindeMixture of Experts Expert Routing
Faculty of Informatics, TU Wien · Independent · UK AI Security Institute
For Those Who Believe in Faithfulness: Optimizing the Area Under Insertion and Deletion Curves for Ranking Relative Feature Importance
Oct 7, 2026Bjørn Leth Møller, Bulat Ibragimov, Christian IgelFeature Attribution Neural Network Interpretability
Department of Computer Science, University of Copenhagen, Denmark
Feature Encoding in VAE-based Audio Decoders: Effects of Input, Depth and Distribution
Oct 6, 2026Louis McCallum, Mick GriersonVariational Autoencoders Audio Representation Learning
Creative Computing Institute, University of the Arts London, London, UK
Interpretable Hypergraph Learning via Neural Additive Models
Oct 5, 2026Shihan Feng, Xin Zheng, Shiyi Yang +3Neural Network Interpretability Hypergraph Neural Networks
School of Data and Information Sciences, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA · Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA · Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA +2
Weight Oracles: Reading Neural Network Weights with Language Models
Oct 5, 2026Krishna Kabra, Constantin Venhoff, Christian Schroeder de WittLLM Auditing Backdoor Detection
University of Oxford
Disentangling Computation in Multi-Task Neural Networks with the Green's Operator
Sep 30, 2026James HazeldenRecurrent Neural Networks Neural Network Interpretability
Applied Mathematics, University of Washington · The Allen Institute Seattle, WA, USA
Synthetic Speech Attribution via Prototypical Networks
Sep 30, 2026Viola Negroni, Paolo Bestagini, Stefano TubaroNeural Network Interpretability
Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano
Certified Approximation for Interpretable Representer Landmarks
Sep 30, 2026Jayanta Mukherjee, Shourya Verma, Mengbo Wang +2Neural Network Interpretability Kernel Methods
Department of Computer Science Purdue University West Lafayette, IN 47907, USA
Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge
Sep 29, 2026Zixing Jia, Yuhang Pan, Ni JiLink Prediction Relational Reasoning
Beijing Institute for Brain Research, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, 102206, China · Chinese Institute for Brain Research, Beijing; Beijing, 102206, China · Beijing Key Laboratory of Brain Science and Brain-Machine Interface +1
Explainability from Training with Applications to TCR-Epitope Prediction
Sep 28, 2026Jiarui Li, Zixiang Yin, Samuel Landry +2Interpretable ML Neural Network Interpretability
Department of Computer Science, Tulane University · Department of Biochemistry and Molecular Biology, Tulane University School of Medicine
Understanding Decision-Making Mechanisms in Neural Routing Solvers
Sep 28, 2026Fatemeh Askari, Mazdak Teymourian, Mohammad Izadi +1Mechanistic Interpretability Neural Network Interpretability
Department of Computer EngineeringSharif University of Technology
Imprint Reader: From Weight-Update Readout to Behavioral Intervention
Sep 28, 2026Guanxu Chen, Qihao Lin, Jing ShaoLLM Interpretability Neural Network Interpretability
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University
Explaining Hyperbolic Neural Networks via Geometry-Aware Relevance Propagation
Sep 28, 2026Ping Xiong, Shanglin Li, Yi Ding +2Neural Network Interpretability Layer-Wise Relevance Propagation
BIFOLD, Germany · Technische Universität Berlin, Germany · Nanyang Technological University, Singapore +3
A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees
Sep 28, 2026Vojtěch Kůr, Adam Kukučka, Tomáš Brázdil +1Concept-Based Explanations Neural Network Interpretability
Masaryk University, Faculty of Informatics, Brno, Czechia
Theory Guided and Interpretable Neural Operator Design for Partial Differential Equation Learning
Sep 27, 2026Zeyuan Song, Zheyu JiangNeural PDE Solvers Neural Network Interpretability
Oklahoma State University Stillwater, OK 74078
Understanding Confabulation and Rethinking Reconstruction in Activation Explanations
Sep 27, 2026Gert Lek, Zixuan Xia, Pin-Yu Chen +1Transformer Interpretability Faithfulness of Language Model Explanations
Universit´e de Neuchˆatel · Universität Bern · IBM Research +1
Fisher Simplicity in Kolmogorov-Arnold Networks and Multilayer Perceptrons
Sep 26, 2026Ami Tavory, Meir FederNeural Network Interpretability Kolmogorov-Arnold Networks
Meta Platforms Tel-Aviv, Israel · School of Electrical and Computer Engineering Tel-Aviv University Tel-Aviv, Israel
Learnable Time-Frequency Masks for Explaining Time-Series Classifiers
Sep 24, 2026Theresa Dahl Frehr, Francisco Pelayo, Lukas Raad +3Feature Attribution Time Series Classification
Department of Applied Mathematics and Computer Science Technical University of Denmark
The Linear Representation Hypothesis Needs a Group Action
Sep 22, 2026Louie Hong Yao, Yuhao Li, Shengchao LiuLinear Representation Hypothesis Neural Network Interpretability
The Chinese University of Hong Kong
Transferring Visual Explanations: How Cross-Architecture Knowledge Distillation Affects Model Interpretability
Sep 20, 2026Aleks Czufarow, Ihor BabinNeural Network Interpretability Cross-Architecture Knowledge Distillation
XIV High School of Stanislaw Staszic,Warsaw,Poland · Ukrainian Catholic University, Lviv, Ukraine
TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data
Sep 17, 2026Kacper Cybiński, Björn van Zwol, James Enouen +5Quantum Machine Learning Neural Network Interpretability
Faculty of Physics, University of Warsaw, Pasteura 5, 02-093 Warsaw, Poland · IDEAS Research Institute, Królewska 27, 00-060 Warsaw, Poland · Applied Quantum Algorithms ⟨aQaL⟩, LIACS & LION, Leiden University, The Netherlands +7
NObSP: Functional Decomposition of Neural Networks via Oblique Subspace Projections
Sep 15, 2026Alexander Caicedo, Víctor De La Hoz, Santiago AlférezFeature Attribution Neural Network Interpretability
Department of Electronic Engineering, Pontificia Universidad Javeriana, Bogot´a, Colombia · Pontificia Universidad Javeriana, Bogot´a, Colombia · Department of Mathematics, Universitat Polit`ecnica de Catalunya, Barcelona, Spain
Interpreting hierarchical organisation of speaker embeddings
Sep 14, 2026Yanze Xu, Wenwu Wang, Mark D. PlumbleySpeech Processing Neural Network Interpretability
Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK · Department of Informatics, King’s College London, London, UK
Interpreting the predictions of neural network classification based on a Taylor Coefficient Analysis (TCA)
Sep 14, 2026Markus Klute, Artur Monsch, Lars Sowa +1Feature Attribution Neural Network Interpretability
Karlsruhe Institute of Technology, Germany
Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessment
Sep 11, 2026Kuan-Chen Wang, Kai-Chun Liu, Ping-Cheng Yeh +2Neural Network Interpretability
Graduate Institute of Communication Engineering, National Taiwan University, Taiwan · Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taiwan · Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan +2
Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models
Sep 9, 2026Yifan Yuan, Xiangyu Liu, Hongming Shan +5Neural Network Interpretability T2I Diffusion Models
Distributed Lag Neural Additive Models
Sep 7, 2026Calle Helmersson, Shivang Pandey, Leonardo Olivetti +1Nonparametric Regression Neural Network Interpretability
Department of Mathematics, KTH Royal Institute of Technology, Stockholm, Sweden · Department of Global Public Health, Karolinska Institutet, Stockholm, Sweden · Swedish Centre for Impacts of Climate Extremes (climes), Uppsala University, Uppsala, Sweden +4
Emergence of Fibrations, Compression, and Symmetry Breaking in Artificial Neural Networks
Sep 1, 2026Osvaldo M Velarde, Lucas C Parra, Alireza Hashemi +1Neural Network Interpretability Neural Network Compression
Levich Institute and Physics Department, City College of New York, 160 Convent Ave, NY, 10031, NY, USA. · Biomedical Engineering Department, City College of New York, 160 Convent Ave, NY, 610101, NY, USA.
Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures
Sep 1, 2026Jaee Ponde, Roshni Agarwal, Subhashis BanerjeeNeural Network Interpretability Convolutional Neural Networks
Truth Audit Labs · Karya AI · Department of Computer Science and the Centre of Digitalisation, AI, and Society, Ashoka University, Sonepat, Haryana, India

Oct 8, 2026, cs.LGJ/K move · Enter open · S save

The Polytopal Neural Network

A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski, Kristoffer Wickstrøm+1

Technical University of Denmark · UiT The Arctic University of Norway

Neural Network Interpretability Geometric Representation Learning Vector Quantization Neural Network Compression

Open paper AskPDF arXiv

Understanding how deep neural networks process information remains a central challenge. Existing interpretability methods often compromise structural fidelity, rely on prespecified corpora, or explain models post-hoc. We propose Polytopal Neural Networks (PNNs), a framework that extracts distinct layer-wise aspects by enforcing a polytope-based structure that is used directly in subsequent information processing. We scale our approach using learned corpus representations and an amortized simplex inference procedure and highlight how the framework also gives a direct route to vector quantized (VQ) training. In PNNs, observations are explicitly described by their alignment with layer-specific aspects. Empirical results show that imposing polytopal constraints on neural network representations preserves meaningful structures in the latent space with minimal degradation in performance, favorable compressed representations when compared to VQ representations in unsupervised learning, while also providing a performant new approach to VQ deep learning training. Our findings suggest that deep networks can enforce interpretable polytope-based representations, offering a principled path toward more transparent AI systems with minimal performance compromise.

Momentum

Related topics

Latest papers 203