Research map / Graph learning / Graph self-supervised learning
Latent Graph Inference with Limited Supervision
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 CUR-based regularization to SLAPS | SLAPS · Pubmed | test accuracy (%): 74.86 ± 0.79 -> 77.12 ± 0.77 | Helped |
| Add CUR-based regularization to GCN+KNN | GCN+KNN · Pubmed | test accuracy (%): 68.66 ± 0.05 -> 74.78 ± 0.17 | Helped |
| Add CUR-based regularization to GRCN | GRCN · Pubmed | test accuracy (%): 69.24 ± 0.20 -> 72.82 ± 1.03 | Helped |
| Add CUR-based regularization to SLAPS | SLAPS · ogbn-arxiv | test accuracy (%): 55.46 ± 0.12 -> 56.11 ± 0.15 | Helped |
| Add CUR-based regularization to SLAPS | SLAPS · Cora390 | test accuracy (%): 76.62 ± 0.83 -> 76.94 ± 0.42 | Helped |
| Add CUR-based regularization to SLAPS | SLAPS · Cora140 | test accuracy (%): 74.26 ± 0.53 -> 75.00 ± 0.49 | Helped |
| Add CUR-based regularization to GCN&KNN | GCN&KNN · Citeseer370 | test accuracy (%): 77.28 ± 0.64 -> 78.48 ± 0.30 | Helped |
| Add CUR-based regularization to SLAPS | SLAPS · Citeseer120 | test accuracy (%): 70.66 ± 0.97 -> 72.36 ± 0.49 | No clear effect |
| Remove all starved nodes rather than retain them (ablation) | GCN+KNN_U · Pubmed | test accuracy (%): 68.66 ± 0.05 -> 74.12 ± 0.32 | Helped |
| Remove all starved nodes rather than retain them (ablation) | SLAPS_U · Pubmed | test accuracy (%): 74.86 ± 0.79 -> 76.74 ± 0.59 | Helped |
| Retain 40% rather than remove all starved nodes (ablation) | GRCN_U · Pubmed | test accuracy (%): 72.80 ± 0.99 -> 73.04 ± 0.52 | No clear effect |
| Increase tau from 25 to 50 (ablation) | GRCN_U · Pubmed | test accuracy (%): 72.80 ± 0.99 -> 71.80 ± 1.13 | Hurt |
Closest papers by meaning
- Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries (ICLR 2024 · similarity 0.88)
- Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness (ICML 2024 · similarity 0.88)
- An Efficient Subgraph-Inferring Framework for Large-Scale Heterogeneous Graphs (AAAI 2024 · similarity 0.86)
- UniGTE: Unified Graph–Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains (NeurIPS 2025 · similarity 0.86)
- Unifying Generation and Prediction on Graphs with Latent Graph Diffusion (NeurIPS 2024 · similarity 0.86)
- GLAD: Improving Latent Graph Generative Modeling with Simple Quantization (AAAI 2025 · similarity 0.86)
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.