Research map / Graph learning / Graph self-supervised learning
DGE: Deep Generative Network Embedding Based on Commonality and Individuality
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 network topology generation to attribute-only variant (DGE-A -> DGE) (ablation) | DGE · Citeseer | Micro-F1: 0.712 -> 0.727 | Helped |
| add network topology generation to attribute-only variant (ablation) | DGE · Cora | Micro-F1: 0.739 -> 0.858 | Helped |
| add network topology generation to attribute-only variant (ablation) | DGE · BlogCatalog | Micro-F1: 0.809 -> 0.931 | Helped |
| add network topology generation to attribute-only variant (ablation) | DGE · Pubmed | Micro-F1: 0.806 -> 0.846 | Helped |
| add attribute generation to network-only variant (DGE-N -> DGE) (ablation) | DGE · Citeseer | Micro-F1: 0.555 -> 0.727 | Helped |
| add attribute generation to network-only variant (ablation) | DGE · Cora | Micro-F1: 0.693 -> 0.858 | Helped |
| add attribute generation to network-only variant (ablation) | DGE · BlogCatalog | Micro-F1: 0.649 -> 0.931 | Helped |
| add attribute generation to network-only variant (ablation) | DGE · Pubmed | Micro-F1: 0.767 -> 0.846 | Helped |
| DGE vs best baseline (PRRE) on node classification | DGE · Cora | Micro-F1: 0.852 -> 0.858 | No clear effect |
| DGE vs strongest baselines on BlogCatalog | DGE · BlogCatalog | Micro-F1: 0.918 -> 0.931 | Helped |
| vary attribute/network embedding dimensions from 2 to 256 | DGE · Cora | F1 | No clear effect |
Closest papers by meaning
- Improving Textual Network Learning with Variational Homophilic Embeddings (NeurIPS 2019 · similarity 0.88)
- Unsupervised Attributed Multiplex Network Embedding (AAAI 2020 · similarity 0.88)
- Efficient Synthetic Network Generation via Latent Embedding Reconstruction (ICML 2026 · similarity 0.87)
- DepthLGP: Learning Embeddings of Out-of-Sample Nodes in Dynamic Networks (AAAI 2018 · similarity 0.87)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.85)
- Non-Euclidean Mixture Model for Social Network Embedding (NeurIPS 2024 · similarity 0.85)
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.