Code classification with graph neural networks: Have you ever struggled to make it work?

Qingchen Yu, Xin Liu, Qingguo Zhou, Jianwei Zhuge, Chunming Wu

Abstract: Highlights•The effect of GNN Layers in the code classification task is confirmed.•Recognizing vulnerable code from real world is proved to be difficult for GNN.•Choosing a proper training strategy matters for learning a good code metric.•The learned code metric could generalize well under few-shot settings.