Entropy-Guided k-Core Pruning Balancing Redundancy Reduction and Information Preservation for Efficient CNN Compression


== Abstract ==

<p>Convolutional Neural Networks (CNNs) are widely used in computer vision, but their massive computational cost and parameter redundancy hinder deployment on resource-constrained devices (e.g., edge terminals). Existing filter pruning methods often struggle to balance two critical goals: aggressive redundancy reduction and effective preservation of taskcritical information&mdash;either leading to excessive accuracy loss or insufficient compression. To address this challenge, we are the first to jointly exploit k-core decomposition and information entropy in a unified pruning criterion, and we instantiate this idea in a novel graph&ndash;entropy collaborative framework that achieves Pareto-optimal compression-accuracy trade-offs. The key steps are as follows: First, we use perceptual hashing (pHash) to calculate the similarity of output feature maps between filters, then model each filter as a node in an undirected graph&mdash;edges are established only when filter similarity exceeds a predefined threshold, forming a &ldquo;redundancy graph&rdquo; that quantifies inter-filter redundancy. Second, kcore decomposition is applied to this graph to identify high-order redundant substructures, which helps locate redundant filters at the structural level. Finally, information entropy is introduced to evaluate the &ldquo;informational value&rdquo; of each node (filter) in the k-core: only filters with low redundancy and high information content are retained, ensuring minimal loss of critical features. Extensive experiments are conducted on CIFAR10 and CIFAR-100 datasets, using representative CNN architectures (VGGNet-16, ResNet-56/110, DenseNet-40). Specifically, VGGNet-16 achieves a 65.8% reduction in floating point operations (FLOPs) and an 88.8% reduction in parameters while experiencing only a 1.24% decrease in Top-1 accuracy. ResNet-56 attains a 50.1% reduction in FLOPs with a nearly imperceptible accuracy loss of 0.03%, markedly surpassing the Fire together wire together (FTWT) method which reduces FLOPs by 54% at the cost of a 1.38% accuracy decline. DenseNet-40 accomplishes a 76.5% FLOPs reduction with a 1.55% accuracy decrease, demonstrating the method&rsquo;s strong applicability for high-intensity compression of densely connected networks. Furthermore, the method&rsquo;s scalability is validated on the large-scale ImageNet dataset with ResNet-50, where it achieves a 73.65% FLOPs reduction with competitive accuracy, underscoring its practicality for real-world applications. These outcomes collectively affirm the effectiveness and broad applicability of the proposed graphentropy collaborative pruning framework.</p>



== Document ==
<pdf>Media:Draft_Sanchez Pinedo_183900412-2524-document.pdf</pdf>