Publications (4)
Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
Jie Wang, Hanzhu Chen, Qitan Lv +7
Inductive link prediction -- where entities during training and inference stages can be different -- has shown great potential for completing evolving knowledge graphs in an entity…
Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs
Jiajun Chen, Huarui He, Feng Wu +1
Inductive link prediction -- where entities during training and inference stages can be different -- has been shown to be promising for completing continuously evolving knowledge g…
Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent Variables
Huarui He, Jie Wang, Yunfei Liu +1
Single-step retrosynthesis is the cornerstone of retrosynthesis planning, which is a crucial task for computer-aided drug discovery. The goal of single-step retrosynthesis is to id…
Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation
Huarui He, Jie Wang, Zhanqiu Zhang +1
Deep graph neural networks (GNNs) have been shown to be expressive for modeling graph-structured data. Nevertheless, the over-stacked architecture of deep graph models makes it dif…