Cover Image

Feature contamination: Neural networks learn uncorrelated features and fail to generalize

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Tianren, Zhao, Chujie, Chen, Guanyu, Jiang, Yizhou, Chen, Feng
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reconciling In-Context and In-Weight Learning via Dual Representation Space Encoding
by: Chen, Guanyu, et al.
Published: (2026)

Preserving Silent Features for Domain Generalization
by: Zhao, Chujie, et al.
Published: (2024)

Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them
by: Chen, Guanyu, et al.
Published: (2025)

A method of supervised learning from conflicting data with hidden contexts
by: Zhang, Tianren, et al.
Published: (2021)

When Do Neural Networks Learn World Models?
by: Zhang, Tianren, et al.
Published: (2025)

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
by: Boix-Adsera, Enric, et al.
Published: (2025)

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

Dynamic feature selection in medical predictive monitoring by reinforcement learning
by: Chen, Yutong, et al.
Published: (2024)

Why does in-context learning fail sometimes? Evaluating in-context learning on open and closed questions
by: Li, Xiang, et al.
Published: (2024)

Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
by: Kunin, Daniel, et al.
Published: (2024)

Negation Neglect: When models fail to learn negations in training
by: Mayne, Harry, et al.
Published: (2026)

When Does Learning Renormalize? Sufficient Conditions for Power Law Spectral Dynamics
by: Zhang, Yizhou
Published: (2025)

Causal invariant geographic network representations with feature and structural distribution shifts
by: Wang, Yuhan, et al.
Published: (2025)

Quantifying and Optimizing Simplicity via Polynomial Representations
by: Zhang, Tianren, et al.
Published: (2026)

Learning Unified Distance Metric for Heterogeneous Attribute Data Clustering
by: Zhang, Yiqun, et al.
Published: (2026)

LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
by: Zhang, Qingyue, et al.
Published: (2025)

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
by: Berglund, Lukas, et al.
Published: (2023)

FEED: Fairness-Enhanced Meta-Learning for Domain Generalization
by: Jiang, Kai, et al.
Published: (2024)

GRAIN: Multi-Granular and Implicit Information Aggregation Graph Neural Network for Heterophilous Graphs
by: Zhao, Songwei, et al.
Published: (2025)

Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
by: Beaglehole, Daniel, et al.
Published: (2024)

Optimal Control Operator Perspective and a Neural Adaptive Spectral Method
by: Feng, Mingquan, et al.
Published: (2024)

Data Curation Through the Lens of Spectral Dynamics: Static Limits, Dynamic Acceleration, and Practical Oracles
by: Zhang, Yizhou, et al.
Published: (2025)

SHAP scores fail pervasively even when Lipschitz succeeds
by: Letoffe, Olivier, et al.
Published: (2024)

Causal Neural Probabilistic Circuits
by: Chen, Weixin, et al.
Published: (2026)

Multi-layer random features and the approximation power of neural networks
by: Takhanov, Rustem
Published: (2024)

FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting
by: Ouyang, Pengpeng, et al.
Published: (2025)

BRIEF: BRain-Inspired network connection search with Extensive temporal feature Fusion enhances disease classification
by: Cui, Xiangxiang, et al.
Published: (2025)

Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
by: Xu, Qi, et al.
Published: (2025)

Physics-informed transfer learning for SHM via feature selection
by: Poole, J., et al.
Published: (2025)

RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical features
by: Song, Jialei, et al.
Published: (2025)

Network Interdiction Goes Neural
by: Zhang, Lei, et al.
Published: (2024)

APF+: Boosting adaptive-potential function reinforcement learning methods with a W-shaped network for high-dimensional games
by: Chen, Yifei, et al.
Published: (2025)

Neural networks for abstraction and reasoning: Towards broad generalization in machines
by: Bober-Irizar, Mikel, et al.
Published: (2024)

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
by: Chen, Weixin, et al.
Published: (2025)

Superposition Yields Robust Neural Scaling
by: Liu, Yizhou, et al.
Published: (2025)

Feature maps for the Laplacian kernel and its generalizations
by: Ahir, Sudhendu, et al.
Published: (2025)

Intrinsic Lorentz Neural Network
by: Shi, Xianglong, et al.
Published: (2026)

Harnessing Contrastive Learning and Neural Transformation for Time Series Anomaly Detection
by: Chen, Katrina, et al.
Published: (2023)

Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning
by: Qiu, Ruizhong, et al.
Published: (2026)

VALUE: Value-Aware Large Language Model for Query Rewriting via Weighted Trie in Sponsored Search
by: Zhang, Xiao, et al.
Published: (2025)