Research map / Graph learning / GNN architectures
Graph Auto-Encoder via Neighborhood Wasserstein Reconstruction
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 degree prediction (ablation) | NWR-GAE · Cornell | accuracy: 54.05 ± 5.97 -> 58.64 ± 5.61 | Helped |
| Use Hungarian matching instead of greedy matching (ablation) | NWR-GAE · Cornell | accuracy: 50.81 ± 4.44 -> 58.64 ± 5.61 | Helped |
| Add neighbor feature distribution reconstruction (ablation) | NWR-GAE · Cornell | accuracy: 49.72 ± 5.04 -> 58.64 ± 5.61 | Helped |
| Use four GNN layers rather than one (ablation) | NWR-GAE · House | homogeneity: 0.89 -> 1.0 | Helped |
| Increase neighborhood sampling size from 5 to 15 (ablation) | NWR-GAE · Chameleon | performance | Helped |
Closest papers by meaning
- NLGT: Neighborhood-based and Label-enhanced Graph Transformer Framework for Node Classification (AAAI 2025 · similarity 0.87)
- The quest for the GRAph Level autoEncoder (GRALE) (NeurIPS 2025 · similarity 0.87)
- Union Subgraph Neural Networks (AAAI 2024 · similarity 0.87)
- GPEN: Global Position Encoding Network for Enhanced Subgraph Representation Learning (ICML 2025 · similarity 0.87)
- GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction (NeurIPS 2024 · similarity 0.87)
- HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning (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.