Research map / Graph learning / Graph self-supervised learning
Distribution-Induced Bidirectional Generative Adversarial Network for Graph Representation Learning
Check 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 structure-aware prior distribution estimation (ablation) | DBGAN · Cora link prediction | AUC: 93.1 -> 94.5 | Helped |
| Add bidirectional adversarial learning (ablation) | DBGAN · Cora link prediction | AUC: 92.5 -> 94.5 | Helped |
| Add both bidirectional adversarial learning and prior distribution estimation (ablation) | DBGAN · Cora link prediction | AUC: 91.0 -> 94.5 | Helped |
| Add structure-aware prior distribution estimation (ablation) | DBGAN · Cora node clustering | ACC: 0.684 -> 0.759 | Helped |
| Add bidirectional adversarial learning (ablation) | DBGAN · Cora node clustering | ACC: 0.535 -> 0.759 | Helped |
| Add both bidirectional adversarial learning and prior distribution estimation (ablation) | DBGAN · Cora node clustering | ACC: 0.596 -> 0.759 | Helped |
| Use DBGAN instead of GALA | Unsupervised graph representations · Cora node clustering | NMI: 0.576 -> 0.560$\pm$0.005 | Hurt |
| Use DBGAN instead of GALA | Unsupervised graph representations · Pubmed node clustering | ARI: 0.321 -> 0.327$\pm$0.02 | Helped |
Closest papers by meaning
- GraphGAN: Graph Representation Learning With Generative Adversarial Nets (AAAI 2018 · similarity 0.91)
- Adversarial Network Embedding (AAAI 2018 · similarity 0.89)
- Adversarial Directed Graph Embedding (AAAI 2021 · similarity 0.88)
- All in a Row: Compressed Convolution Networks for Graphs (ICML 2023 · similarity 0.87)
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective (NeurIPS 2025 · similarity 0.86)
- GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation (ICLR 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.