Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models

Chun Kit Wong; Paraskevas Pegios; Nina Weng; Emilie Pi Fogtmann Sejer; Martin Grønnebæk Tolsgaard; Anders Nymark Christensen; Aasa Feragen

Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models

Chun Kit Wong, Paraskevas Pegios, Nina Weng, Emilie Pi Fogtmann Sejer, Martin Grønnebæk Tolsgaard, Anders Nymark Christensen, Aasa Feragen

CAMES

Originalsprog	Engelsk
Udgiver	arXiv
Status	Udgivet - 15 dec. 2025

Adgang til dokumentet

https://arxiv.org/abs/2512.13144

Citationsformater

@misc{c140ad59a8ad43e6b91b4069b2ca9095,

title = "Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models",

author = "Wong, \{Chun Kit\} and Paraskevas Pegios and Nina Weng and Sejer, \{Emilie Pi Fogtmann\} and Tolsgaard, \{Martin Gr{\o}nneb{\ae}k\} and Christensen, \{Anders Nymark\} and Aasa Feragen",

year = "2025",

month = dec,

day = "15",

language = "English",

publisher = "arXiv",

type = "WorkingPaper",

institution = "arXiv",

}

TY - UNPB

T1 - Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models

AU - Wong, Chun Kit

AU - Pegios, Paraskevas

AU - Weng, Nina

AU - Sejer, Emilie Pi Fogtmann

AU - Tolsgaard, Martin Grønnebæk

AU - Christensen, Anders Nymark

AU - Feragen, Aasa

PY - 2025/12/15

Y1 - 2025/12/15

M3 - Preprint

BT - Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models

PB - arXiv

ER -