Research map / Graph learning / GNN architectures
NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search
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 NAS search algorithms (access to 2% of architectures) instead of picking from top 5% architectures | NAS-Bench-Graph search · Cora | accuracy: 80.63 -> 82.27 | Helped |
| random search vs learned NAS strategies (RL, EA, GNAS, Auto-GNN) | NAS-Bench-Graph search · Nine datasets | accuracy: Cora 82.09 vs RL 82.27 | No clear effect |
| mutate architecture choices (operations vs macro space) instead of random architecture pairs | GraphNAS evolutionary search · Nine datasets | accuracy difference | Helped |
| generate architectures from deeper parts first (reverse order) instead of natural order | RL-based GraphNAS · Nine datasets | eta-squared | Helped |
| transfer best architecture from similar dataset | GraphNAS · Cross-dataset | top-5% overlap: overlap no larger than 0.3 | Hurt |
Closest papers by meaning
- NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search (ICLR 2020 · similarity 0.91)
- NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks (NeurIPS 2022 · similarity 0.91)
- Graph HyperNetworks for Neural Architecture Search (ICLR 2019 · similarity 0.91)
- Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective (ICLR 2025 · similarity 0.90)
- Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks (ICML 2023 · similarity 0.90)
- NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise (NeurIPS 2024 · 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.