Lun Hu — accepted AI-conference papers

2026

Patient-Visit-Spanned Hypergraph Learning for EHR-based Diagnosis Prediction

IJCAI 2026

Hypergraphs effectively model complex interactions in structured Electronic Health Records (EHR). Consequently, Hypergraph Neural Networks (HGNNs) are commonly applied to EHR-based diagnosis prediction. However, existing HGNNs struggle to capture patient-visit long-range dependencies when processing

Cited by 0 Scholar ↗

2024

Dual-Channel Learning Framework for Drug-Drug Interaction Prediction via Relation-Aware Heterogeneous Graph Transformer

Xiaorui Su, Pengwei Hu, Zhu-Hong You, Philip S. Yu, Lun Hu

AAAI 2024technical

Identifying novel drug-drug interactions (DDIs) is a crucial task in pharmacology, as the interference between pharmacological substances can pose serious medical risks. In recent years, several network-based techniques have emerged for predicting DDIs. However, they primarily focus on local structu…

Cited by 17 Source ↗PDF ↗Scholar ↗