no code implementations • 17 Sep 2022 • Long Yu, Zhicong Luo, Huanyong Liu, Deng Lin, Hongzhu Li, Yafeng Deng
Translation-based knowledge graph embedding has been one of the most important branches for knowledge representation learning since TransE came out.
2 code implementations • 27 May 2022 • Hongzhu Li, Xiangrui Gao, Linhui Feng, Yafeng Deng, Yuhui Yin
Conventional representation learning algorithms for knowledge graphs (KG) map each entity to a unique embedding vector, ignoring the rich information contained in the neighborhood.
Ranked #6 on Link Property Prediction on ogbl-wikikg2
2 code implementations • 24 Apr 2019 • Hongzhu Li, Weiqiang Wang
The outputs of a CTC-trained model tend to form a series of spikes separated by strongly predicted blanks, know as the spiky problem.