2 code implementations • 6 Dec 2021 • Zhitao Wang, Yong Zhou, Litao Hong, Yuanhang Zou, Hanjing Su, Shouzhi Chen
The framework treats link prediction as a pairwise learning to rank problem and consists of four main components, i. e., neighborhood encoder, link predictor, negative sampler and objective function.
Ranked #1 on Link Property Prediction on ogbl-citation2