Quantized Graph Neural Networks for Image Classification

Quantized Graph Neural Networks for Image Classification

Researchers have resorted to model quantization to compress and accelerate graph neural networks (GNNs). Nevertheless, several challenges remain: (1) quantization functions overlook outliers in the distribution, leading to increased quantization errors; (2) the reliance on full-precision teacher mod...

Full description

Bibliographic Details
Main Authors: Xinbiao Xu, Liyan Ma, Tieyong Zeng, Qinghua Huang
Format: Article
Language:English
Published: MDPI AG 2023-12-01
Series:Mathematics
Subjects:
graph neural network
model quantization
knowledge distillation
image classification
Online Access:https://www.mdpi.com/2227-7390/11/24/4927

Internet

https://www.mdpi.com/2227-7390/11/24/4927

Similar Items