IEEE

An End-to-End Training Method to Ensemble Bi-Linear Models for Knowledge Graph Completion

Abstract: The study of ensemble learning in knowledge graph embedding (KGE) shows that combining multiple individual KGE models can perform better on knowledge graph completion. However, existing KGE ...
IEEE

Local Unidentifiability of EdgeWeights for Linear Systems with Graph Laplacian

Abstract: In this paper, we analyze the local identifiability of parameters in linear systems whose system matrix is given by a graph Laplacian. Graph Laplacian is a matrix given by a graph and the ...