Pruning and Quantization Impact on Graph Neural Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912669831790592 |
|---|---|
| author | Khedri, Khatoon Rawassizadeh, Reza Wen, Qifu Hosseinzadeh, Mehdi |
| author_facet | Khedri, Khatoon Rawassizadeh, Reza Wen, Qifu Hosseinzadeh, Mehdi |
| contents | 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 reduce the model size while maintaining reasonable accuracy. Two of the common neural network compression techniques include pruning and quantization. In this research, we empirically examine the effects of three pruning methods and three quantization methods on different GNN models, including graph classification tasks, node classification tasks, and link prediction. We conducted all experiments on three graph datasets, including Cora, Proteins, and BBBP. Our findings demonstrate that unstructured fine-grained and global pruning can significantly reduce the model's size(50\%) while maintaining or even improving precision after fine-tuning the pruned model. The evaluation of different quantization methods on GNN shows diverse impacts on accuracy, inference time, and model size across different datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_22058 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pruning and Quantization Impact on Graph Neural Networks Khedri, Khatoon Rawassizadeh, Reza Wen, Qifu Hosseinzadeh, Mehdi Machine Learning 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 reduce the model size while maintaining reasonable accuracy. Two of the common neural network compression techniques include pruning and quantization. In this research, we empirically examine the effects of three pruning methods and three quantization methods on different GNN models, including graph classification tasks, node classification tasks, and link prediction. We conducted all experiments on three graph datasets, including Cora, Proteins, and BBBP. Our findings demonstrate that unstructured fine-grained and global pruning can significantly reduce the model's size(50\%) while maintaining or even improving precision after fine-tuning the pruned model. The evaluation of different quantization methods on GNN shows diverse impacts on accuracy, inference time, and model size across different datasets. |
| title | Pruning and Quantization Impact on Graph Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.22058 |