Research map / Graph learning / Graph self-supervised learning
Directed Graph Auto-Encoders
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 a single-layer rather than two-layer encoder (ablation) | DiGAE · CoraML directed link prediction | AUC: 88.10 +/- 1.70 -> 94.09 +/- 0.66 | Helped |
| Use a single-layer rather than two-layer encoder (ablation) | DiGAE · CiteSeer directed link prediction | AUC: 92.05 +/- 1.06 -> 92.76 +/- 0.87 | Helped |
| Use a single-layer rather than two-layer encoder (ablation) | DiGAE · Pubmed directed link prediction | AUC: 92.09 +/- 1.92 -> 94.35 +/- 0.37 | Helped |
| Tune the degree-normalization exponents alpha and beta (ablation) | DiGAE-1L · CoraML directed link prediction | AUC: 73.73% | Helped |
| Tune the degree-normalization exponents alpha and beta (ablation) | DiGAE-1L · CiteSeer directed link prediction | AUC: 86.10% | Helped |
| Use DiGAE-1L instead of truncated SVD with 16-dimensional embeddings | Directed link prediction · CoraML | AP: 82.83% -> 94.10% | Helped |
| Use DiGAE-1L instead of truncated SVD with 16-dimensional embeddings | Directed link prediction · CiteSeer | AP: 69.88% -> 92.57% | Helped |
Closest papers by meaning
- Graph Auto-Encoder via Neighborhood Wasserstein Reconstruction (ICLR 2022 · similarity 0.88)
- Dual Low-Rank Graph Autoencoder for Semantic and Topological Networks (AAAI 2023 · similarity 0.88)
- Effective Decoding in Graph Auto-Encoder Using Triadic Closure (AAAI 2020 · similarity 0.88)
- Autobahn: Automorphism-based Graph Neural Nets (NeurIPS 2021 · similarity 0.88)
- The quest for the GRAph Level autoEncoder (GRALE) (NeurIPS 2025 · similarity 0.87)
- DUPLEX: Dual GAT for Complex Embedding of Directed Graphs (ICML 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.