Tweeted By @ml_review
Pre-training Graph Neural Networks
— ML Review (@ml_review) May 31, 2019
By @weihua916 @liubowen16
Combining both node- and graph-level pre-training techniques significantly improves generalization to out-of-distribution graphshttps://t.co/Re4eXZBdyR pic.twitter.com/sUZNhEBon9