研究剪枝与量化对图神经网络的影响，发现细粒度剪枝可减半模型大小且提升精度。
Pruning and Quantization Impact on Graph Neural Networks
- 对比三种剪枝与三种量化方法在GNN上的效果
- 细粒度剪枝使模型缩小50%后精度仍保持或提升
- 量化对不同数据集的推理速度和精度影响差异大
图神经网络（GNN）在图结构数据学习中表现优异，但计算与资源开销高。为降低模型规模并维持合理精度，常采用剪枝与量化等压缩技术。本文针对Cora、Proteins、BBBP三个图数据集，系统评估了三种剪枝方法和三种量化方法在图分类、节点分类及链接预测任务中的表现。实验结果表明，非结构化细粒度剪枝与全局剪枝可将模型规模减少50%，并在微调后实现精度保持甚至提升；不同量化方法对准确率、推理时间及模型大小的影响在不同数据集间存在显著差异。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。