arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.04528cs.LG
收藏

利用信道修剪加速大规模实时的GNN推理

Accelerating Large Scale Real-Time GNN Inference using Channel Pruning

University of Southern California(南加州大学);US Army Research Lab(美国陆军研究实验室)

Hongkuan Zhou, Ajitesh Srivastava, Hanqing Zeng, Rajgopal Kannan, Viktor Prasanna

摘要:

图神经网络(GNN)被证明是为下游应用生成节点嵌入的强大模型。然而,由于GNN推理的高计算复杂度,很难将GNN部署用于大规模或实时的【形】应用。在本文中,我们建议通过修剪每层中的维度来加速GNN推理,而精度损失可以忽略不计。我们的修剪框架使用了一种新的LASSO回归公式来识别对输出激活有很大影响的特征维度(通道)。我们确定了两个推理方案和设计修剪方案的基础上,他们的计算和内存使用。为了进一步降低推理复杂度,我们有效地存储和重用访问节点的隐藏特征,这大大减少了计算目标嵌入所需的支持节点的数量。我们评估所提出的方法与节点分类问题的五个流行的数据集和一个实时的【形】垃圾邮件检测应用程序。我们证明,修剪GNN模型大大减少了计算和内存的使用,几乎没有精度损失。对于完整的推理,该方法实现了平均3.27倍的加速比,只有0.002下降在GPU上的F1-Micro。对于批量推理,所提出的方法实现了平均6.67倍的加速比,而CPU上的F1-Micro仅下降0.003。据我们所知,我们是第一个通过通道修剪来加速大规模实时的【形】GNN推理的人。

英文摘要:

Graph Neural Networks (GNNs) are proven to be powerful models to generate node embedding for downstream applications. However, due to the high computation complexity of GNN inference, it is hard to deploy GNNs for large-scale or real-time applications. In this paper, we propose to accelerate GNN inference by pruning the dimensions in each layer with negligible accuracy loss. Our pruning framework uses a novel LASSO regression formulation for GNNs to identify feature dimensions (channels) that have high influence on the output activation. We identify two inference scenarios and design pruning schemes based on their computation and memory usage for each. To further reduce the inference complexity, we effectively store and reuse hidden features of visited nodes, which significantly reduces the number of supporting nodes needed to compute the target embedding. We evaluate the proposed method with the node classification problem on five popular datasets and a real-time spam detection application. We demonstrate that the pruned GNN models greatly reduce computation and memory usage with little accuracy loss. For full inference, the proposed method achieves an average of 3.27x speedup with only 0.002 drop in F1-Micro on GPU. For batched inference, the proposed method achieves an average of 6.67x speedup with only 0.003 drop in F1-Micro on CPU. To the best of our knowledge, we are the first to accelerate large scale real-time GNN inference through channel pruning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑