paper-with-me

Papers

Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning

2023-06-30 · Hichem Sahbi

Magnitude pruning is one of the mainstream methods in lightweight architecture design whose goal is to extract subnetworks with the largest weight connections. This method is known to be successful, but under very high pruning regimes, it suffers from topological inconsistency which renders the extracted subnetworks disconnected, and this hinders their generalization ability. In this paper, we devise a novel magnitude pruning method that allows extracting subnetworks while guarantying their topological consistency. The latter ensures that only accessible and co-accessible -- impactful -- connections are kept in the resulting lightweight networks. Our solution is based on a novel reparametrization and two supervisory bi-directional networks which implement accessibility/co-accessibility and guarantee that only connected subnetworks will be selected during training. This solution allows enhancing generalization significantly, under very high pruning regimes, as corroborated through extensive experiments, involving graph convolutional networks, on the challenging task of skeleton-based action recognition.

📄 PDF Abstract BibTeX arXiv:2306.17590

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionSkeleton Based Action Recognition

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Lightweight Graph Convolutional Networks with Topologically Consistent Magnitude Pruning

2022-03-25 · Hichem Sahbi

Graph convolution networks (GCNs) are currently mainstream in learning with irregular data. These models rely on message passing and attention mechanisms that capture context and node-to-node relationships. With multi-he…

Complementary Attention Head Pruning for Efficient Transformers

2026-06-17 · Yaniv Livertovsky, Shahar Somin, Gonen Singer arxiv

The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments.…

LEAN: graph-based pruning for convolutional neural networks by extracting longest chains

2020-11-13 · Richard Schoonhoven, Allard A. Hendriksen, Daniël M. Pelt, K. Joost Batenburg

Neural network pruning techniques can substantially reduce the computational cost of applying convolutional neural networks (CNNs). Common pruning methods determine which convolutional filters to remove by ranking the fi…

Network Pruning

LEAN: graph-based pruning for convolutional neural networks by extracting longest chains

2021-09-29 · Richard Arnoud Schoonhoven, Allard Hendriksen, Daniel Pelt, Joost Batenburg

Neural network pruning techniques can substantially reduce the computational cost of applying convolutional neural networks (CNNs). Common pruning methods determine which convolutional filters to remove by ranking the fi…

Network Pruning

Pruning Graph Convolutional Networks to select meaningful graph frequencies for fMRI decoding

2022-03-09 · Yassine El Ouahidi, Hugo Tessier, Giulia Lioi, Nicolas Farrugia 외

Graph Signal Processing is a promising framework to manipulate brain signals as it allows to encompass the spatial dependencies between the activity in regions of interest in the brain. In this work, we are interested in…