Imagen de Portada

Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Aguilar, Leonel, Nagler, Jan, Hoelscher, Christoph, Antulov-Fantulin, Nino
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards agent-based-model informed neural networks
por: Antulov-Fantulin, Nino
Publicado: (2025)

Stretched and measured neural predictions of complex network dynamics
por: Vasiliauskaite, Vaiva, et al.
Publicado: (2023)

Identifying Representations for Intervention Extrapolation
por: Saengkyongam, Sorawit, et al.
Publicado: (2023)

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
por: Kachaev, Nikita, et al.
Publicado: (2025)

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

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

NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
por: Esteves, Bernardo, et al.
Publicado: (2024)

SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
por: Ding, Mucong, et al.
Publicado: (2024)

Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
por: Mao, Yixiu, et al.
Publicado: (2024)

Identifying Bias in Deep Neural Networks Using Image Transforms
por: Erukude, Sai Teja, et al.
Publicado: (2024)

Uncertainty Quantification for Prior-Data Fitted Networks using Martingale Posteriors
por: Nagler, Thomas, et al.
Publicado: (2025)

Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins
por: Ray, Rahul D
Publicado: (2026)

Diverging Flows: Detecting Extrapolations in Conditional Generation
por: Tsakonas, Constantinos, et al.
Publicado: (2026)

Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data
por: Zhang, Bingjie, et al.
Publicado: (2025)

Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood
por: Yao, Qingmao, et al.
Publicado: (2025)

It Ain't That Bad: Understanding the Mysterious Performance Drop in OOD Generalization for Generative Transformer Models
por: Xu, Xingcheng, et al.
Publicado: (2023)

On the Utilization of Unique Node Identifiers in Graph Neural Networks
por: Bechler-Speicher, Maya, et al.
Publicado: (2024)

From Shallow Bayesian Neural Networks to Gaussian Processes: General Convergence, Identifiability and Scalable Inference
por: de Araújo, Gracielle Antunes, et al.
Publicado: (2026)

Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks
por: Zhang, Jiaxing, et al.
Publicado: (2025)

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
por: Hu, Yuanzhe, et al.
Publicado: (2025)

A Relational Inductive Bias for Dimensional Abstraction in Neural Networks
por: Campbell, Declan, et al.
Publicado: (2024)

Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning
por: Liu, Siyuan, et al.
Publicado: (2026)

Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs
por: Ma, Xin, et al.
Publicado: (2024)

MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
por: Kim, Donghwan, et al.
Publicado: (2026)

Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modeling
por: Shen, Xu, et al.
Publicado: (2025)

Physics-informed Attention-enhanced Fourier Neural Operator for Solar Magnetic Field Extrapolations
por: Cao, Jinghao, et al.
Publicado: (2025)

Benchmarking Fairness in Spiking Neural Networks: Data Bias, Spurious Features, and Hardware Effects
por: He, Hudi, et al.
Publicado: (2026)

Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
por: Razin, Noam, et al.
Publicado: (2024)

Operator Feature Neural Network for Symbolic Regression
por: Deng, Yusong, et al.
Publicado: (2024)

SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
por: Xie, Qihu, et al.
Publicado: (2025)

The Extrapolation Power of Implicit Models
por: Decugis, Juliette, et al.
Publicado: (2024)

Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
por: Jian, Chengtao, et al.
Publicado: (2024)

RL Fine-Tuning Heals OOD Forgetting in SFT
por: Jin, Hangzhan, et al.
Publicado: (2025)

TAO-Net: Two-stage Adaptive OOD Classification Network for Fine-grained Encrypted Traffic Classification
por: Wang, Zihao, et al.
Publicado: (2025)

Does Your Wildfire Prediction Model Actually Work, or Just Score Well?
por: Xu, Yangshuang, et al.
Publicado: (2026)

Quotient Geometry, Effective Curvature, and Implicit Bias in Simple Shallow Neural Networks
por: Dong, Hang-Cheng, et al.
Publicado: (2026)

Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
por: Fang, Ronglong, et al.
Publicado: (2024)

Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks
por: Bencomo, Gianluca, et al.
Publicado: (2025)

The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity
por: Sahs, Justin, et al.
Publicado: (2025)

Unveiling the Power of Sparse Neural Networks for Feature Selection
por: Atashgahi, Zahra, et al.
Publicado: (2024)