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 ...
Scientific Research Publishing

Graph Neural Networks for Anomaly Detection in Cloud Infrastructure ()

Graph Neural Networks for Anomaly Detection in Cloud Infrastructure ...
IEEE

Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations

Abstract: This paper focuses on representation learning for dynamic graphs with temporal interactions. A fundamental issue is that both the graph structure and the nodes own their own dynamics, and ...