87 Papers
669 Citations
Jie Wang is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Computer science & Lasso (statistics). The author has an hindex of 21, co-authored 69 publications. Previous affiliations of Jie Wang include Arizona State University & Florida State University.
Chat about Author
Papers
Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
Zhanqiu Zhang,Jianyu Cai,Yongdong Zhang,Jie Wang +3 more
- 03 Apr 2020
TL;DR: A novel knowledge graph embedding model, Hierarchy-Aware Knowledge Graph Embedding (HAKE), which maps entities into the polar coordinate system and significantly outperforms existing state-of-the-art methods on benchmark datasets for the link prediction task.
•Posted Content
Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
TL;DR: Huang et al. as mentioned in this paper proposed Hierarchy-Aware Knowledge Graph Embedding (HAKE), which maps entities into the polar coordinate system to model semantic hierarchies.
Epidemic spread in weighted scale-free networks
TL;DR: In this article, the authors investigate the detailed epidemic spreading process in scale-free networks with links' weights that denote familiarity between two individuals and find that spreading velocity reaches a peak quickly then decays in a power-law form.
162
•Posted Content
Lasso Screening Rules via Dual Polytope Projection
Jie Wang,Peter Wonka,Jieping Ye +2 more
TL;DR: In this article, the authors proposed an efficient and effective screening rule via Dual Polytope Projections (DPP), which is mainly based on the uniqueness and nonexpansiveness of the optimal dual solution due to the fact that the feasible set in the dual space is a convex and closed polytope.
158
Line Graph Neural Networks for Link Prediction.
TL;DR: Wang et al. as mentioned in this paper considered the graph link prediction problem, which is a classic graph analytical problem with many real-world applications, and proposed to seek a radically different and novel path by making use of the line graphs in graph theory.
158