A graph-spectral importance score based on layer-wise structural distortion between pre- and post-activation neuron graphs identifies removable neurons for iterative pruning without intermediate updates, followed by recovery fine-tuning.
Communications of the ACM , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Analytic framework yields exact induced norms ||A||_{q→r} for key matrix classes and exact values for associated Grothendieck problems.
citing papers explorer
-
Spectral structural distortion reveals redundant neurons in neural networks
A graph-spectral importance score based on layer-wise structural distortion between pre- and post-activation neuron graphs identifies removable neurons for iterative pruning without intermediate updates, followed by recovery fine-tuning.
-
On the Induced Norms of Matrices and Grothendieck problems
Analytic framework yields exact induced norms ||A||_{q→r} for key matrix classes and exact values for associated Grothendieck problems.