论文标题
学位：图形神经网络的量化感知培训
Degree-Quant: Quantization-Aware Training for Graph Neural Networks
论文作者
论文摘要
图形神经网络（GNN）由于能够对非均匀结构化数据进行建模，因此在各种任务上表现出了强大的性能。尽管他们承诺，但很少有研究探索方法，使它们在推理时间更有效。在这项工作中，我们探讨了训练量化的GNN的生存能力，从而在推理过程中可以使用低精度整数算术。我们确定试图量化GNN时出现的唯一出现的错误源，并提出一种构建剂量的方法，即学士学位，以提高在其他体系结构（例如CNN）上使用的现有量化量化训练基线的性能。我们在六个数据集上验证我们的方法，并显示与以前的尝试不同，该模型概括为看不见的图。在大多数情况下，接受INT8量化的学位训练的模型以及FP32模型的模型；对于INT4型号，我们比基线获得了多达26％的收益。使用INT8算术时，我们的工作最多可在CPU上进行4.7倍的加速。
Graph neural networks (GNNs) have demonstrated strong performance on a wide variety of tasks due to their ability to model non-uniform structured data. Despite their promise, there exists little research exploring methods to make them more efficient at inference time. In this work, we explore the viability of training quantized GNNs, enabling the usage of low precision integer arithmetic during inference. We identify the sources of error that uniquely arise when attempting to quantize GNNs, and propose an architecturally-agnostic method, Degree-Quant, to improve performance over existing quantization-aware training baselines commonly used on other architectures, such as CNNs. We validate our method on six datasets and show, unlike previous attempts, that models generalize to unseen graphs. Models trained with Degree-Quant for INT8 quantization perform as well as FP32 models in most cases; for INT4 models, we obtain up to 26% gains over the baselines. Our work enables up to 4.7x speedups on CPU when using INT8 arithmetic.
