Graph neural networks (GNNs) have been a hot spot of recent research and are widely utilized in diverse applications. However, with the use of huger data and deeper models, an urgent demand is unsurprisingly made to accelerate GNNs for more efficient execution. In this paper, we provide a comprehensive survey on acceleration methods for GNNs from an algorithmic perspective. We first present a new taxonomy to classify existing acceleration methods into five categories. Based on the classification, we systematically discuss these methods and highlight their correlations. Next, we provide comparisons from aspects of the efficiency and characteristics of these methods. Finally, we suggest some promising prospects for future research.
翻译:神经网络(GNNs)是近期研究的一个热点,广泛用于各种应用,然而,由于使用更大型的数据和更深的模型,人们毫不奇怪地迫切需要加快GNNs,以便更有效地执行。在本文件中,我们从算法的角度对GNNs加速方法进行了全面调查。我们首先提出一个新的分类法,将现有的加速方法分为五类。根据分类法,我们系统地讨论这些方法,并突出其相互关系。接下来,我们比较了这些方法的效率和特点。最后,我们提出了未来研究的一些前景。