Research map / Graph learning / Graph self-supervised learning
Graph-Driven Generative Models for Heterogeneous Multi-Task Learning
Wenlin Wang, Hongteng Xu, Zhe Gan, Bai Li, Guoyin Wang, Liqun Chen, Qian Yang, Wenqi Wang, Lawrence Carin
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 |
|---|---|---|---|
| jointly train heterogeneous tasks with a shared GCN and task-specific VAEs | GD-VAE · MIMIC-III clinical topic modeling | NPMI: 0.142 -> 0.151 | Improved |
| add procedure recommendation to topic modeling (ablation) | GD-VAE · MIMIC-III Small, 10 topics | NPMI: 0.142 -> 0.147 | Improved |
| add admission-type prediction to topic modeling (ablation) | GD-VAE · MIMIC-III Small, 10 topics | NPMI: 0.142 -> 0.142 | No clear effect |
| jointly train heterogeneous tasks with a shared GCN and task-specific VAEs | GD-VAE · MIMIC-III procedure recommendation, Small, Top-1 | F1: 31.1 -> 31.8 | Improved |
| add topic modeling to procedure recommendation (ablation) | GD-VAE · MIMIC-III Small, Top-1 | F1: 31.1 -> 31.6 | Improved |
| add admission-type prediction to procedure recommendation (ablation) | GD-VAE · MIMIC-III Small, Top-1 | F1: 31.1 -> 31.3 | Improved |
| jointly train heterogeneous tasks with a shared GCN and task-specific VAEs | GD-VAE · MIMIC-III admission-type prediction, Small | F1: 86.91 -> 88.01 | Improved |
| add procedure recommendation to admission-type prediction (ablation) | GD-VAE · MIMIC-III Small | F1: 86.91 -> 87.93 | Improved |
| add topic modeling to admission-type prediction (ablation) | GD-VAE · MIMIC-III Small | F1: 86.91 -> 87.22 | Improved |
| use PMI edges between ICD codes and TF-IDF edges between codes and admissions instead of the tested graph variants (ablation) | GD-VAE · MIMIC-III healthcare tasks | performance | Improved |
Closest papers by meaning
- HeterGP: Bridging Heterogeneity in Graph Neural Networks with Multi-View Prompting (AAAI 2025 · similarity 0.88)
- Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees (ICML 2025 · similarity 0.86)
- HePa: Heterogeneous Graph Prompting for All-Level Classification Tasks (AAAI 2025 · similarity 0.86)
- HGPrompt: Bridging Homogeneous and Heterogeneous Graphs for Few-Shot Prompt Learning (AAAI 2024 · similarity 0.86)
- GOFA: A Generative One-For-All Model for Joint Graph Language Modeling (ICLR 2025 · similarity 0.84)
- Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach (AAAI 2025 · similarity 0.84)
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.
