
		<paper>
			<loc>https://jjcit.org/paper/306</loc>
			<title>FILTER SPECTRAL EFFICIENCY (FSE): STRUCTURED NETWORK PRUNING VIA INTER-LAYER SPECTRAL COUPLING</title>
			<doi>10.5455/jjcit.71-1783883615</doi>
			<authors>Soumia Laroui,Hamida Seba,Karima Amrouche,Yassine Ait Ali Yahia</authors>
			<keywords>Structured pruning,Data-free pruning,Inter-layer spectral coupling,Singular value decomposition,Deep neural networks</keywords>
			<views>1016</views>
			<downloads>352</downloads>
			<received_date>12-Jul.-2026</received_date>
			<revised_date>  2-Sep.-2026 and 4-Sep.-2026</revised_date>
			<accepted_date>  4-Sep.-2026</accepted_date>
			<abstract>Structured filter pruning is an effective approach for reducing the computational cost of deep neural networks 
while preserving efficient deployment on standard hardware. However, most existing pruning methods evaluate 
filters independently, overlooking the inter-layer spectral coupling between consecutive layers, while many high-
performing approaches rely on activation statistics or calibration data. We propose Filter Spectral Efficiency 
(FSE), a data-free structured pruning framework that estimates filter importance through the spectral coupling 
between adjacent layers. FSE constructs singular-value-based filter descriptors, builds inter-layer coupling 
matrices, derives a spectral pruning criterion and allocates sparsity through a global adaptive budget. Extensive 
experiments on five CNN architectures for CIFAR-10 and ResNet-50 on ImageNet demonstrate that FSE 
consistently achieves a favorable accuracy-compression trade-off, outperforming representative structured 
pruning methods at comparable parameter and FLOP reductions. On CIFAR-10, FSE reduces the FLOPs of 
ResNet-56 by 59.8% with only a 0.07 percentage point accuracy drop and prunes GoogLeNet by 70.7% FLOPs 
while improving Top-1 accuracy over H Rank by 0.73 percentage points. On ImageNet, FSE improves the Top-1 
accuracy of ResNet-50 by 1.14 percentage points over H Rank at a comparable FLOP reduction. These results 
demonstrate that inter-layer spectral coupling provides an effective and practical foundation for data-free 
structured network pruning.</abstract>
		</paper>


