Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modeling

arXiv:2403.05752v1 Announce Type: new
Abstract: A Knowledge Graph (KG) is a heterogeneous graph encompassing a diverse range of node and edge types. Heterogeneous Graph Neural Networks (HGNNs) are popular for training machine learning tasks like node classification and link prediction on KGs. However, HGNN methods exhibit excessive complexity influenced by the KG's size, density, and the number of node and edge types. AI practitioners handcraft a subgraph of a KG G relevant to a specific task. We refer to this …

abstract arxiv classification complexity cs.ai cs.lg diverse edge gnns graph graph neural networks graphs however knowledge knowledge graph knowledge graphs link prediction machine machine learning modeling networks neural networks node popular prediction tasks training type types