Designing Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition
Deep neural networks (DNNs) are nowadays witnessing a major success in solving many pattern recognition tasks including skeleton-based classification. The deployment of DNNs on edge-devices, endowed with limited time and memory resources, requires designing lightweight and efficient variants of these networks. Pruning is one of the lightweight network design techniques that operate by removing unnecessary network parts, in a structured or an unstructured manner, including individual weights, neurons or even entire channels. Nonetheless, structured and unstructured pruning methods, when applied separately, may either be inefficient or ineffective. In this paper, we devise a novel semi-structured method that discards the downsides of structured and unstructured pruning while gathering their upsides to some extent. The proposed solution is based on a differentiable cascaded parametrization which combines (i) a band-stop mechanism that prunes weights depending on their magnitudes, (ii) a weight-sharing parametrization that prunes connections either individually or group-wise, and (iii) a gating mechanism which arbitrates between different group-wise and entry-wise pruning. All these cascaded parametrizations are built upon a common latent tensor which is trained end-to-end by minimizing a classification loss and a surrogate tensor rank regularizer. Extensive experiments, conducted on the challenging tasks of action and hand-gesture recognition, show the clear advantage of our proposed semi-structured pruning approach against both structured and unstructured pruning, when taken separately, as well as the related work.
Code (0)
등록된 구현이 없습니다.
Tasks
Gesture RecognitionHand Gesture RecognitionHand-Gesture RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Simple and Deep Graph Convolutional Networks
Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datas…
Graph ClassificationGraph RegressionLink PredictionNode Classification+2Progressive Binarization with Semi-Structured Pruning for LLMs
Large language models (LLMs) have achieved remarkable success in natural language processing tasks, but their high computational and memory demands pose challenges for deployment on resource-constrained devices. Binariza…
BinarizationStructured Pruning for Deep Convolutional Neural Networks: A survey
The remarkable performance of deep Convolutional neural networks (CNNs) is generally attributed to their deeper and wider architectures, which can come with significant computational costs. Pruning neural networks has th…
Network PruningNeural Architecture SearchSurveyLearning Coarse-to-Fine Pruning of Graph Convolutional Networks for Skeleton-based Recognition
Magnitude Pruning is a staple lightweight network design method which seeks to remove connections with the smallest magnitude. This process is either achieved in a structured or unstructured manner. While structured prun…
Progressive Graph Convolutional Networks for Semi-Supervised Node Classification
Graph convolutional networks have been successful in addressing graph-based tasks such as semi-supervised node classification. Existing methods use a network structure defined by the user based on experimentation with fi…
ClassificationGeneral ClassificationNode Classification