Cargando…
Degree-Aware Graph Neural Network Quantization
In this paper, we investigate the problem of graph neural network quantization. Despite the great success on convolutional neural networks, directly applying current network quantization approaches to graph neural networks faces two challenges. First, the fixed-scale parameter in the current methods...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10670813/ https://www.ncbi.nlm.nih.gov/pubmed/37998202 http://dx.doi.org/10.3390/e25111510 |
_version_ | 1785140006711459840 |
---|---|
author | Fan, Ziqin Jin, Xi |
author_facet | Fan, Ziqin Jin, Xi |
author_sort | Fan, Ziqin |
collection | PubMed |
description | In this paper, we investigate the problem of graph neural network quantization. Despite the great success on convolutional neural networks, directly applying current network quantization approaches to graph neural networks faces two challenges. First, the fixed-scale parameter in the current methods cannot flexibly fit diverse tasks and network architectures. Second, the variations of node degree in a graph leads to uneven responses, limiting the accuracy of the quantizer. To address these two challenges, we introduce learnable scale parameters that can be optimized jointly with the graph networks. In addition, we propose degree-aware normalization to process nodes with different degrees. Experiments on different tasks, baselines, and datasets demonstrate the superiority of our method against previous state-of-the-art ones. |
format | Online Article Text |
id | pubmed-10670813 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-106708132023-11-02 Degree-Aware Graph Neural Network Quantization Fan, Ziqin Jin, Xi Entropy (Basel) Article In this paper, we investigate the problem of graph neural network quantization. Despite the great success on convolutional neural networks, directly applying current network quantization approaches to graph neural networks faces two challenges. First, the fixed-scale parameter in the current methods cannot flexibly fit diverse tasks and network architectures. Second, the variations of node degree in a graph leads to uneven responses, limiting the accuracy of the quantizer. To address these two challenges, we introduce learnable scale parameters that can be optimized jointly with the graph networks. In addition, we propose degree-aware normalization to process nodes with different degrees. Experiments on different tasks, baselines, and datasets demonstrate the superiority of our method against previous state-of-the-art ones. MDPI 2023-11-02 /pmc/articles/PMC10670813/ /pubmed/37998202 http://dx.doi.org/10.3390/e25111510 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Fan, Ziqin Jin, Xi Degree-Aware Graph Neural Network Quantization |
title | Degree-Aware Graph Neural Network Quantization |
title_full | Degree-Aware Graph Neural Network Quantization |
title_fullStr | Degree-Aware Graph Neural Network Quantization |
title_full_unstemmed | Degree-Aware Graph Neural Network Quantization |
title_short | Degree-Aware Graph Neural Network Quantization |
title_sort | degree-aware graph neural network quantization |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10670813/ https://www.ncbi.nlm.nih.gov/pubmed/37998202 http://dx.doi.org/10.3390/e25111510 |
work_keys_str_mv | AT fanziqin degreeawaregraphneuralnetworkquantization AT jinxi degreeawaregraphneuralnetworkquantization |