Research map / Graph learning / Knowledge and temporal graphs
Knowledge-Enhanced Explainable Hypergraph Convolution Network for Medication Recommendation
Zihan Zhang, Hongzhi Liu, Xiaoshuang Guo, Tianqi Sun, Zhonghai Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add hypergraph convolution for co-occurrence (ablation) | KEHGCN · MIMIC-III-MED | Jaccard: 0.3810 -> 0.3999 | Improved |
| add metapath convolution (semantic knowledge) (ablation) | KEHGCN · MIMIC-IV-GU | DDI rate: 0.2059 -> 0.1312 | Improved |
| use hypergraph convolution instead of standard GCN (ablation) | KEHGCN · MIMIC-IV-OMED | Jaccard: 0.3578 -> 0.3688 | Improved |
| add prior weights on metapath types (ablation) | KEHGCN · MIMIC-IV-GU | DDI rate: 0.1607 -> 0.1312 | Improved |
| add prior weights on metapath types (ablation) | KEHGCN · MIMIC-III-MED | Jaccard: 0.3950 -> 0.3999 | Improved |
| add metapath convolution (ablation) | KEHGCN · MIMIC-IV-OMED | F1: 0.4802 -> 0.5001 | Improved |
| KEHGCN vs best baseline LAMRec | KEHGCN · MIMIC-III-MED | Jaccard: 0.3929 -> 0.3999 | Improved |
| KEHGCN vs LAMRec | KEHGCN · MIMIC-IV-GU | DDI rate: 0.1861 -> 0.1312 | Improved |
| set both DDI and contraindication loss weights to 1 (vs zero) (ablation) | KEHGCN · MIMIC-III-MED | F1 and DDI rate | Mixed |
| set DDI loss weight to 1 with contraindication weight 0 (ablation) | KEHGCN · MIMIC-III-MED | DDI rate | Improved |
Closest papers by meaning
- GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs (ICLR 2024 · similarity 0.86)
- SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language Models (ICML 2025 · similarity 0.85)
- Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval (ICLR 2025 · similarity 0.84)
- Semantic Enhanced Heterogeneous Hypergraph Network for Collaborative Filtering (AAAI 2025 · similarity 0.84)
- HI-DR: Exploiting Health Status-Aware Attention and an EHR Graph+ for Effective Medication Recommendation (AAAI 2025 · similarity 0.84)
- Hypergraph Representation Learning with Hyperlink Random Effects (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
