Cover Image

Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lim, Jinwoo, Kim, Suhyun, Moon, Soo-Mook
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Convergence Analysis of Federated Learning Methods Using Backward Error Analysis
by: Lim, Jinwoo, et al.
Published: (2025)

CURing Large Models: Compression via CUR Decomposition
by: Park, Sanghyeon, et al.
Published: (2025)

BugSweeper: Function-Level Detection of Smart Contract Vulnerabilities Using Graph Neural Networks
by: Lee, Uisang, et al.
Published: (2025)

Lipschitz-aware Linearity Grafting for Certified Robustness
by: Han, Yongjin, et al.
Published: (2025)

FRAIN to Train: A Fast-and-Reliable Solution for Decentralized Federated Learning
by: Park, Sanghyeon, et al.
Published: (2025)

Feature Identification via the Empirical NTK
by: Lin, Jennifer
Published: (2025)

Explicit Feature Interaction-aware Graph Neural Networks
by: Kim, Minkyu, et al.
Published: (2022)

Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles
by: Kim, Jung-hun, et al.
Published: (2017)

Debiasing Online Preference Learning via Preference Feature Preservation
by: Kim, Dongyoung, et al.
Published: (2025)

Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime
by: Wang, Yuqing, et al.
Published: (2025)

OPC: One-Point-Contraction Unlearning Toward Deep Feature Forgetting
by: Jung, Jaeheun, et al.
Published: (2025)

Reactivation: Empirical NTK Dynamics Under Task Shifts
by: Liu, Yuzhi, et al.
Published: (2025)

NTK-Guided Few-Shot Class Incremental Learning
by: Liu, Jingren, et al.
Published: (2024)

Connecting NTK and NNGP: A Unified Theoretical Framework for Wide Neural Network Learning Dynamics
by: Avidan, Yehonatan, et al.
Published: (2023)

Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts
by: Khanh, Truong Xuan, et al.
Published: (2026)

MPruner: Optimizing Neural Network Size with CKA-Based Mutual Information Pruning
by: Hu, Seungbeom, et al.
Published: (2024)

Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
by: Nam, Jaehyun, et al.
Published: (2024)

RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear Programs
by: Lee, Tae-Hoon, et al.
Published: (2024)

Random at First, Fast at Last: NTK-Guided Fourier Pre-Processing for Tabular DL
by: Sergazinov, Renat, et al.
Published: (2025)

BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
by: Lee, Changwoo, et al.
Published: (2024)

Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation
by: Choi, Yoonhyuk, et al.
Published: (2022)

Multi-View Graph Convolution Network for Internal Talent Recommendation Based on Enterprise Emails
by: Kim, Soo Hyun, et al.
Published: (2025)

Influence Functions for Edge Edits in Non-Convex Graph Neural Networks
by: Heo, Jaeseung, et al.
Published: (2025)

Three Mechanisms of Feature Learning in a Linear Network
by: Xu, Yizhou, et al.
Published: (2024)

Combining Causal Models for More Accurate Abstractions of Neural Networks
by: Pîslar, Theodora-Mara, et al.
Published: (2025)

FnRGNN: Distribution-aware Fairness in Graph Neural Network
by: Park, Soyoung, et al.
Published: (2025)

From Black-Box to White-Box: Control-Theoretic Neural Network Interpretability
by: Moon, Jihoon
Published: (2025)

Attention-Based Neural-Augmented Kalman Filter for Legged Robot State Estimation
by: Lee, Seokju, et al.
Published: (2026)

Linear Mode Connectivity in Sparse Neural Networks
by: McDermott, Luke, et al.
Published: (2023)

FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
by: Chung, Hyunsuk, et al.
Published: (2026)

Less Is More -- On the Importance of Sparsification for Transformers and Graph Neural Networks for TSP
by: Lischka, Attila, et al.
Published: (2024)

Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption
by: Kim, Sunwoo, et al.
Published: (2025)

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

Quantile-Free Uncertainty Quantification in Graph Neural Networks
by: park, Soyoung, et al.
Published: (2026)

The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
by: Cha, Taehun, et al.
Published: (2026)

Shortcut to Nowhere: Demystifying Deep Spurious Regression
by: Xu, Guanrong, et al.
Published: (2026)

Mitigating Shortcut Learning with InterpoLated Learning
by: Korakakis, Michalis, et al.
Published: (2025)

Learning with Logical Constraints but without Shortcut Satisfaction
by: Li, Zenan, et al.
Published: (2024)

Pathwise Explanation of ReLU Neural Networks
by: Lim, Seongwoo, et al.
Published: (2025)

Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
by: Dong, Yushun, et al.
Published: (2024)