GPPT阅读笔记

2022年KDD刚中的文章，GNN领域第一篇用prompt实现self-supervised learning的文章。

Motivation

They rarely notice the inherent training objective gap between the pretext and downstream tasks. This significant gap often requires costly fine-tuning for adapting the pre-trained model to downstream problem, which prevents the efficient elicitation of pre-trained knowledge and then results in poor results

Contribution

To bridge the task gap, we propose a novel transfer learning paradigm to generalize GNNs, namely graph pre-training and prompt tuning (GPPT).

Pre-train: Link Prediction

Downstream: Node Classification

Framework