Cover Image

Through a Steerable Lens: Magnifying Neural Network Interpretability via Phase-Based Extrapolation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mahdisoltani, Farzaneh, Mahdisoltani, Saeed, Grosse, Roger B., Fleet, David J.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Minimal Framework for Optimizing Vaccination Protocols Targeting Highly Mutable Pathogens
by: Mahdisoltani, Saeed, et al.
Published: (2024)

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens
by: Nadaf, Mohammed Suhail B
Published: (2026)

Clifford-Steerable Convolutional Neural Networks
by: Zhdanov, Maksim, et al.
Published: (2024)

Towards Understanding Extrapolation: a Causal Lens
by: Kong, Lingjing, et al.
Published: (2025)

On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
by: Gravina, Alessio, et al.
Published: (2024)

Engression: Extrapolation through the Lens of Distributional Regression
by: Shen, Xinwei, et al.
Published: (2023)

Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks
by: Grillo, Niccolò, et al.
Published: (2025)

Quantized Convolutional Neural Networks Through the Lens of Partial Differential Equations
by: Ben-Yair, Ido, et al.
Published: (2021)

Deep Neural Networks Tend To Extrapolate Predictably
by: Kang, Katie, et al.
Published: (2023)

Extrapolability Improvement of Machine Learning-Based Evapotranspiration Models via Domain-Adversarial Neural Networks
by: Shi, Haiyang
Published: (2024)

Beyond Scaling Curves: Internal Dynamics of Neural Networks Through the NTK Lens
by: Nikolaou, Konstantin, et al.
Published: (2025)

Steerable Neural ODEs on Homogeneous Spaces
by: Andersdotter, Emma, et al.
Published: (2026)

Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
by: Kulkarni, Akshay, et al.
Published: (2025)

Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
by: Campi, Francesco, et al.
Published: (2023)

Enhancing Quantum Variational Algorithms with Zero Noise Extrapolation via Neural Networks
by: Bhattacharjee, Subhasree, et al.
Published: (2024)

Tractable Shapley Values and Interactions via Tensor Networks
by: Heidari, Farzaneh, et al.
Published: (2025)

Calibration through the Lens of Interpretability
by: Torabian, Alireza, et al.
Published: (2024)

The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
by: Mueller, Aaron, et al.
Published: (2024)

Manifold-Orthogonal Dual-spectrum Extrapolation for Parameterized Physics-Informed Neural Networks
by: Liang, Zhangyong, et al.
Published: (2026)

A Personalized Video-Based Hand Taxonomy: Application for Individuals with Spinal Cord Injury
by: Dousty, Mehdy, et al.
Published: (2024)

Enhancing Neural Network Interpretability Through Conductance-Based Information Plane Analysis
by: Dabounou, Jaouad, et al.
Published: (2024)

Generalization of Graph Neural Networks through the Lens of Homomorphism
by: Li, Shouheng, et al.
Published: (2024)

Detecting Out-of-Distribution Through the Lens of Neural Collapse
by: Liu, Litian, et al.
Published: (2023)

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks
by: Lee, Dongwoo, et al.
Published: (2025)

How Interpretable Are Interpretable Graph Neural Networks?
by: Chen, Yongqiang, et al.
Published: (2024)

Function Extrapolation with Neural Networks and Its Application for Manifolds
by: Hay, Guy, et al.
Published: (2024)

Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications
by: Paul, Debdas, et al.
Published: (2026)

On Logical Extrapolation for Mazes with Recurrent and Implicit Networks
by: Knutson, Brandon, et al.
Published: (2024)

Training Data Attribution via Approximate Unrolled Differentiation
by: Bae, Juhan, et al.
Published: (2024)

Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders
by: Marks, Luke, et al.
Published: (2024)

Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes
by: Kobalczyk, Katarzyna, et al.
Published: (2024)

Trend Extrapolation for Technology Forecasting: Leveraging LSTM Neural Networks for Trend Analysis of Space Exploration Vessels
by: Tsai, Peng-Hung, et al.
Published: (2025)

Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks
by: Lee, Hunjae
Published: (2025)

AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks
by: Wei, Yi, et al.
Published: (2026)

Stable and Steerable Sparse Autoencoders with Weight Regularization
by: Jedryszek, Piotr, et al.
Published: (2026)

Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries
by: Kolb, Chris, et al.
Published: (2025)

Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation
by: Lucena, Anaísa, et al.
Published: (2026)

Learning a Sparse Neural Network using IHT
by: Damadi, Saeed, et al.
Published: (2024)

Why Cannot Neural Networks Master Extrapolation? Insights from Physical Laws
by: Dakhmouche, Ramzi, et al.
Published: (2025)

Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
by: Aguilar, Leonel, et al.
Published: (2026)