no code implementations • 14 Feb 2024 • Zhao Li, Xin Wang, JianXin Li, Wenbin Guo, Jun Zhao
Existing knowledge hypergraph embedding methods mainly focused on improving model performance, but their model structures are becoming more complex and redundant.
no code implementations • 11 Dec 2023 • Wenbin Guo, Zhao Li, Xin Wang, Zirui Chen
In this paper, we propose a novel dynamic convolutional embedding model ConvD for knowledge graph completion, which directly reshapes the relation embeddings into multiple internal convolution kernels to improve the external convolution kernels of the traditional convolutional embedding model.
no code implementations • 20 Oct 2021 • Yueyan Chu, Wenbin Guo, Kangyong You, Lei Zhao, Tao Peng, Wenbo Wang
Then we utilize the K-means clustering method to obtain the rough locations of the off-grid sources as the initial feasible point of the ML estimator.