{"type":"ScholarlyArticle","title":"Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks","authors":[{"name":"Pengyong Li","slug":"pengyong-li","given":"Pengyong","family":"Li","affiliation":""},{"name":"Jun Wang","slug":"jun-wang","given":"Jun","family":"Wang","affiliation":""},{"name":"Ziliang Li","slug":"ziliang-li","given":"Ziliang","family":"Li","affiliation":""},{"name":"Yixuan Qiao","slug":"yixuan-qiao","given":"Yixuan","family":"Qiao","affiliation":""},{"name":"Xianggen Liu","slug":"xianggen-liu","given":"Xianggen","family":"Liu","affiliation":""},{"name":"Fei Ma","slug":"fei-ma","given":"Fei","family":"Ma","affiliation":""},{"name":"Peng Gao","slug":"peng-gao","given":"Peng","family":"Gao","affiliation":""},{"name":"Sen Song","slug":"sen-song","given":"Sen","family":"Song","affiliation":""},{"name":"Guotong Xie","slug":"guotong-xie","given":"Guotong","family":"Xie","affiliation":""}],"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.","doi":"10.24963/ijcai.2021/371","url":"https://ijcai.org/proceedings/2021/371","pdf":"https://ijcai.org/proceedings/2021/0371.pdf","markdown":"https://ijcai.org/proceedings/2021/371.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/371","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning","track":"Main Track","number":371,"pages":{"first":2694,"last":2700},"keywords":["Machine Learning: Unsupervised Learning","Machine Learning: Deep Learning","Data Mining: Mining Graphs, Semi Structured Data, Complex Data"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}