Research map / Graph learning / Graph self-supervised learning
GraphGAN: Graph Representation Learning With Generative Adversarial Nets
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 |
|---|---|---|---|
| Use adversarial training with a generator and discriminator instead of single-model graph embedding | GraphGAN · arXiv-AstroPh and arXiv-GrQc | Accuracy: 1.18% to 4.27%; 0.59% to 11.13% | Helped |
| Use adversarial training with a generator and discriminator instead of single-model graph embedding | GraphGAN · BlogCatalog and Wikipedia | Accuracy: 1.75% to 13.17%; 0.95% to 21.71% | Helped |
| Use GraphGAN instead of the listed graph embedding baselines | GraphGAN · MovieLens-1M | Precision@20: 38.56%; 59.60%; 124.95%; 156.85% | Helped |
| Use GraphGAN instead of the listed graph embedding baselines | GraphGAN · MovieLens-1M | Recall@20: at least 52.33% | Helped |
| Use graph softmax rather than traditional full softmax for the generator | GraphGAN generator · Graph representation learning | computational efficiency: O(V · d log V) -> O(d log V) | Helped |
| Use a proximity-aware graph softmax that incorporates shortest-path structure | GraphGAN generator · arXiv-AstroPh and arXiv-GrQc | shortest-distance and edge-existence correlation (R²): 0.831; 0.710 | Helped |
Closest papers by meaning
- Distribution-Induced Bidirectional Generative Adversarial Network for Graph Representation Learning (CVPR 2020 · similarity 0.91)
- NetGAN without GAN: From Random Walks to Low-Rank Approximations (ICML 2020 · similarity 0.90)
- NetGAN: Generating Graphs via Random Walks (ICML 2018 · similarity 0.90)
- Adversarial Directed Graph Embedding (AAAI 2021 · similarity 0.89)
- Unsupervised Adversarially Robust Representation Learning on Graphs (AAAI 2022 · similarity 0.89)
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective (NeurIPS 2025 · 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.