Research map / Graph learning / GNN architectures
Graph Stochastic Neural Networks for Semi-supervised Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 stochastic latent variable (GSNN-M) to GCN aggregation | GCN · Cora, standard split | accuracy: 81.49 -> 83.94 | Helped |
| add stochastic latent variable (GSNN-A) to GAT aggregation | GAT · Pubmed, standard split | accuracy: 78.57 -> 78.99 | Helped |
| GSNN vs best baselines in standard scenario | GSNN-M · Citeseer, standard split | accuracy: 72.20 vs G3NN 73.10 | No clear effect |
| add stochastic latent variable (GSNN-M) to GCN | GCN · Cora 1% labels, no early stopping | accuracy: 66.58 -> 71.76 | Helped |
| GSNN-A vs GCN with scarce labels | GCN · Pubmed 0.1% labels | accuracy: 69.21 -> 73.17 | Helped |
| add stochastic latent variable (GSNN-M) to GCN under Meta-Train attack | GCN · Cora, Meta-Train attack | accuracy: 76.25 -> 84.57 | Helped |
| GSNN-M vs BGCN under Meta-Self attack | BGCN · Cora, Meta-Self attack | accuracy: 81.29 -> 80.13 | Hurt |
Closest papers by meaning
- Almost Surely Asymptotically Constant Graph Neural Networks (NeurIPS 2024 · similarity 0.90)
- Learning Latent Graph Structures and their Uncertainty (ICML 2025 · similarity 0.89)
- A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion (NeurIPS 2026 · similarity 0.89)
- Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks (ICLR 2024 · similarity 0.88)
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.88)
- Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification (ICML 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.