Research map / Architectures and efficiency / Neural architecture search
TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search
Check 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 |
|---|---|---|---|
| Initialize evolutionary search with the top 10 architectures from the source task | REA · Across examined tasks | average search performance | Helped |
| Transfer the PPO policy pretrained on Jigsaw to the target task | PPO · Cell-level and macro-level search spaces | search performance | Hurt |
| Transfer the best architecture from another task instead of searching on the target task | Random Search · Cell-level and macro-level search spaces | task performance | Hurt |
| Add a task-context encoder and candidate-performance evaluator to policy transfer | PPO-transfer · Object Classification (macro-level) | accuracy: 46.76±0.5 -> 47.29±0.3 | Helped |
| Use CATCH rather than PPO-transfer | PPO-transfer · Room Layout (cell-level) | L2 loss: 62.01±1.0 -> 60.70±0.7 | Mixed |
Closest papers by meaning
- NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks (NeurIPS 2022 · similarity 0.93)
- NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search (ICLR 2020 · similarity 0.93)
- Generic Neural Architecture Search via Regression (NeurIPS 2021 · similarity 0.93)
- NAS-Bench-101: Towards Reproducible Neural Architecture Search (ICML 2019 · similarity 0.93)
- NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search (AAAI 2021 · similarity 0.92)
- einspace: Searching for Neural Architectures from Fundamental Operations (NeurIPS 2024 · similarity 0.91)
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.