Research map / Graph learning / Graph self-supervised learning
Graph Representation Learning via Ladder Gamma Variational Autoencoders
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 node side-information (LGVG-X vs LGVG) (ablation) | LGVG · Cora link prediction | Average Precision: 0.9254 ± 0.0068 -> 0.9502 ± 0.0061 | Helped |
| add node side-information (LGVG-X vs LGVG) (ablation) | LGVG · Citeseer link prediction | Average Precision: 0.9130 ± 0.0112 -> 0.9624 ± 0.0067 | Helped |
| add node side-information (LGVG-X vs LGVG) (ablation) | LGVG · Pubmed link prediction | Average Precision: 0.9545 ± 0.0024 -> 0.9559 ± 0.0017 | Helped |
| add node side-information (LGVG-X vs LGVG) (ablation) | LGVG · NIPS12 link prediction | Average Precision: 0.9260 ± 0.0068 -> 0.9260 ± 0.0068 | No clear effect |
| replace single-layer EPM-SGVB with deep ladder gamma VAE (ablation) | EPM-SGVB · Cora link prediction | Average Precision: 0.8666 ± 0.0109 -> 0.9254 ± 0.0068 | Helped |
| replace single-layer EPM-SGVB with deep ladder gamma VAE (ablation) | EPM-SGVB · Pubmed link prediction | Average Precision: 0.8600 ± 0.0047 -> 0.9545 ± 0.0024 | Helped |
| increase number of stochastic layers (1 to 5) (ablation) | LGVG · NIPS12 link prediction | ROC/AP | Helped |
| use LGVG instead of VGAE | VGAE · Cora link prediction | Average Precision: 0.9260 ± 0.0001 -> 0.9254 ± 0.0068 | Mixed |
| use LGVG instead of DGLFRM | DGLFRM · Citeseer link prediction | Average Precision: 0.9438 ± 0.0073 -> 0.9130 ± 0.0112 | Hurt |
| LGVG-X vs VGAE with less training data | VGAE · Cora link prediction | Average Precision | Helped |
Closest papers by meaning
- vGraph: A Generative Model for Joint Community Detection and Node Representation Learning (NeurIPS 2019 · similarity 0.90)
- From Link Prediction to Linear Community Detection: A Finite-Sample Guarantee for Graph Pretraining (NeurIPS 2026 · similarity 0.90)
- Dual Low-Rank Graph Autoencoder for Semantic and Topological Networks (AAAI 2023 · similarity 0.89)
- Community-Aware Variational Autoencoder for Continuous Dynamic Networks (AAAI 2025 · similarity 0.87)
- GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction (NeurIPS 2024 · similarity 0.87)
- HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning (NeurIPS 2024 · similarity 0.87)
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.