Graph Pruning for Model Compression

2019-11-22 · Mingyang Zhang, Xinyi Yu, Jingtao Rong, Linlin Ou

Previous AutoML pruning works utilized individual layer features to automatically prune filters. We analyze the correlation for two layers from the different blocks which have a short-cut structure. It shows that, in one block, the deeper layer has many redundant filters which can be represented by filters in the former layer. So, it is necessary to take information from other layers into consideration in pruning. In this paper, a novel pruning method, named GraphPruning, is proposed. Any series of the network is viewed as a graph. To automatically aggregate neighboring features for each node, a graph aggregator based on graph convolution networks(GCN) is designed. In the training stage, a PruningNet that is given aggregated node features generates reasonable weights for any size of the sub-network. Subsequently, the best configuration of the Pruned Network is searched by reinforcement learning. Different from previous work, we take the node features from a well-trained graph aggregator instead of the hand-craft features, as the states in reinforcement learning. Compared with other AutoML pruning works, our method has achieved the state-of-the-art under the same conditions on ImageNet-2012.

📄 PDF Abstract BibTeX arXiv:1911.09817

Code (0)

등록된 구현이 없습니다.

Tasks

AutoMLmodelModel Compression reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Pruning and Quantization Impact on Graph Neural Networks

2025-10-24 · Khatoon Khedri, Reza Rawassizadeh, Qifu Wen, Mehdi Hosseinzadeh arxiv

Graph neural networks (GNNs) are known to operate with high accuracy on learning from graph-structured data, but they suffer from high computational and resource costs. Neural network compression methods are used to redu…

Neural Network Compression Graph Classification Node Classification Link Prediction

Mapping Text to Multiplex Graph: Prompt Compression as Lévy Walk-Guided Graph Pruning

2026-05-04 · Yaxin Gao, Yao Lu, Jinhong Deng, Jiaqi Nie 외 arxiv

Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is often spread across multiple locations and connected through both local…

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

2021-02-05 · Sixing Yu, Arya Mazaheri, Ali Jannesari

Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on para…

Graph Embedding Model Compression Network Pruning reinforcement-learning+1

Conditional Automated Channel Pruning for Deep Neural Networks

2020-09-21 · Yixin Liu, Yong Guo, Zichang Liu, Haohua Liu 외

Model compression aims to reduce the redundancy of deep networks to obtain compact models. Recently, channel pruning has become one of the predominant compression methods to deploy deep models on resource-constrained dev…

Model Compression

MINT: Deep Network Compression via Mutual Information-based Neuron Trimming

2020-03-18 · Madan Ravi Ganesh, Jason J. Corso, Salimeh Yasaei Sekeh

Most approaches to deep neural network compression via pruning either evaluate a filter's importance using its weights or optimize an alternative objective function with sparsity constraints. While these methods offer a …

Neural Network Compression