Research map / Graph learning / GNN architectures
Diffusion-Guided Graph Data Augmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
The paper proposes a diffusion-guided approach to graph data augmentation to improve GNN generalization and reduce overfitting on limited or low-diversity graph datasets.
Problem
GNNs trained on limited or low-diversity graph datasets overfit and memorize, hurting generalization; existing graph data augmentation methods rely on simple transformations.
Approach
Uses diffusion models to guide graph data augmentation, going beyond simple structural or feature transformations. Details beyond the abstract are not available.
Closest papers by meaning
- Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning (ICLR 2025 · similarity 0.89)
- Unifying Generation and Prediction on Graphs with Latent Graph Diffusion (NeurIPS 2024 · similarity 0.88)
- Learning to Approximate Adaptive Kernel Convolution on Graphs (AAAI 2024 · similarity 0.88)
- Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models (NeurIPS 2025 · similarity 0.88)
- Graph Neural Network Generalization With Gaussian Mixture Model Based Augmentation (ICML 2025 · similarity 0.88)
- Graph Classification via Reference Distribution Learning: Theory and Practice (NeurIPS 2024 · similarity 0.88)
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.