AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation

Chenxin Li, Xinyu Liu, Cheng Wang, Yifan Liu, Weihao Yu, Jing Shao, Yixuan Yuan

ECCV 2024 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 29 citations (OpenAlex)

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 changedWhereMeasuredEffect
add graph-prompted completion instead of zero-filling missing modality (ablation)GTP-4o · TCGA-GBMLGGGlioma grading AUC: 0.9087 -> 0.9389Improved
add graph-prompted completion instead of dropping missing modality (ablation)GTP-4o · TCGA-GBMLGGGlioma grading AUC: 0.9288 -> 0.9389Improved
add heterogeneous embedding instead of homogeneous graph (ablation)GTP-4o · TCGA-GBMLGGGlioma grading AUC: 0.9232 -> 0.9389Improved
add heterogeneous relations on edges (ablation)GTP-4o · TCGA-GBMLGGSurvival C-Index: 0.8201 -> 0.8416Improved
add prompt bank (ablation)GTP-4o completion · TCGA-GBMLGGSurvival C-Index: 0.8280 -> 0.8416Improved
add knowledge-guided hierarchical aggregation instead of plain mean (ablation)GTP-4o · TCGA-GBMLGGSurvival C-Index: 0.8311 -> 0.8416Improved
use knowledge-derived meta-paths instead of random meta-paths (ablation)GTP-4o aggregation · TCGA-GBMLGGGlioma grading AUC: 0.9350 -> 0.9389Improved
add cell graph and text modalities to genomics and imagesGTP-4o · TCGA-GBMLGGGlioma grading AUC: 0.9256 -> 0.9336 -> 0.9389Improved
use multimodal (G+I) instead of unimodal inputsbaselines and GTP-4o · TCGA-GBMLGGGlioma grading AUC: GTP-4o G+I 0.9256 vs HEAT image-only 0.9289Mixed
GTP-4o versus TransFusion with four modalitiesGTP-4o · TCGA-KIRCSurvival C-Index: 0.7289 -> 0.7336Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy