主题(音乐)
计算机科学
图形
人工智能
自然语言处理
理论计算机科学
声学
物理
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence
[Association for the Advancement of Artificial Intelligence (AAAI)]
日期:2021-05-18
卷期号:35 (18): 15980-15981
被引量:13
标识
DOI:10.1609/aaai.v35i18.17986
摘要
We propose a MOTIF-driven contrastive framework to pretrain a graph neural network in a self-supervised manner so that it can automatically mine motifs from large graph datasets. Our framework achieves state-of-the-art results on various graph-level downstream tasks with few labels, like molecular property prediction.
科研通智能强力驱动
Strongly Powered by AbleSci AI