Research map / Graph learning / Graph self-supervised learning
Deep Neural Networks for Learning Graph Representations
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 |
|---|---|---|---|
| weight context by distance (α=0.98 vs α=1) (ablation) | DNGR · 20-NewsGroup 3NG | NMI: 74.63 -> 80.44 | Helped |
| use stacked denoising autoencoder instead of SVD on PPMI (ablation) | DNGR · 20-NewsGroup 3NG | NMI: 62.95 -> 80.44 | Helped |
| use stacked denoising autoencoder instead of SVD (ablation) | DNGR · WS353 | Spearman: 72.22 -> 72.45 | Helped |
| increase embedding dimension 128->512 | DeepWalk/SGNS · 20-NewsGroup | NMI | No clear effect |
| use deeper layers of the autoencoder (ablation) | DNGR · 20-NewsGroup 3NG | NMI: 62.84 -> 80.44 | Helped |
| apply dimension reduction to PPMI matrix | PPMI · WS Relatedness | Spearman: 56.02 -> 68.73 | Helped |
| DNGR vs DeepWalk | graph embedding · 20-NewsGroup 9NG | NMI: 46.86 -> 59.13 | Helped |
Closest papers by meaning
- Representation Learning on Graphs with Jumping Knowledge Networks (ICML 2018 · similarity 0.89)
- GraphGAN: Graph Representation Learning With Generative Adversarial Nets (AAAI 2018 · similarity 0.89)
- Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings (NeurIPS 2020 · similarity 0.88)
- Learning Graph Representation via Graph Entropy Maximization (ICML 2024 · similarity 0.87)
- Learning Latent Graph Structures and their Uncertainty (ICML 2025 · similarity 0.87)
- Learning Representations for Hierarchies with Minimal Support (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.