Name
Title | ||
|---|---|---|
Pairwise Half-graph Discrimination - A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks. |
Abstract | ||
|---|---|---|
Self-supervised learning has gradually emerged as a powerful technique for graph representation learning. However, transferable, generalizable, and robust representation learning on graph data still remains a challenge for pre-training graph neural networks. In this paper, we propose a simple and effective self-supervised pre-training strategy, named Pairwise Half-graph Discrimination (PHD), that explicitly pre-trains a graph neural network at graph-level. PHD is designed as a simple binary classification task to discriminate whether two half-graphs come from the same source. Experiments demonstrate that the PHD is an effective pre-training strategy that offers comparable or superior performance on 13 graph classification tasks compared with state-of-the-art strategies, and achieves notable improvements when combined with node-level strategies. Moreover, the visualization of learned representation revealed that PHD strategy indeed empowers the model to learn graph-level knowledge like the molecular scaffold. These results have established PHD as a powerful and effective self-supervised learning strategy in graph-level representation learning. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.24963/ijcai.2021/371 | IJCAI |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 9 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Pengyong Li | 1 | 1 | 1.71 |
| Jun Wang | 2 | 51 | 16.17 |
| Ziliang Li | 3 | 0 | 0.34 |
| Yixuan Qiao | 4 | 1 | 2.05 |
| Xianggen Liu | 5 | 3 | 2.07 |
| Fei Ma | 6 | 0 | 0.34 |
| Peng Gao | 7 | 7 | 12.93 |
| Sen Song | 8 | 299 | 22.35 |
| Guotong Xie | 9 | 0 | 1.35 |