.png){kind=icon}
返回
Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2023.3285874.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph convolutional networks (GCNs) are widely used in a variety of applications and can be seen as an unstructured version of standard convolutional neural networks (CNNs). As in CNNs, the computational cost of GCNs for large input graphs (such as large point clouds or meshes) can be high and inhibit the use of these networks, especially in environments with low computational resources. To ease these costs, quantization can be applied to GCNs. However, aggressive quantization of the feature maps can lead to a significant degradation in performance. On a different note, the Haar wavelet transforms are known to be one of the most effective and efficient approaches to compress signals. Therefore, instead of applying aggressive quantization to feature maps, we propose to use Haar wavelet compression and light quantization to reduce the computations involved with the network. We demonstrate that this approach surpasses aggressive feature quantization by a significant margin, for a variety of problems ranging from node classification to point cloud classification and both part and semantic segmentation.
Keyword:
Graph convolutional networks (GCNs)
graph wavelet transform
network compression
quantized neural networks
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Conjugated heat transfer and temperature distributions in a gas turbine combustion liner under base-load operation基本负荷运行下燃气轮机燃烧衬里中的共轭传热和温度分布
PREAI
分享收藏M-GWNN: Multi-granularity graph wavelet neural networks for semi-supervised node classification.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏SAR Image segmentation based on convolutional-wavelet neural network and markov random field基于卷积小波神经网络和马尔可夫随机场的SAR图像分割PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容