Research map / Architectures and efficiency / Neural architecture search
Hierarchical Representations for Efficient 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 evolutionary search instead of random search with 200 samples | Hierarchical representation · CIFAR-10 test | error (%): 4.04 ± 0.2 -> 3.75 ± 0.12 | Helped |
| Use evolutionary search instead of random search with 200 samples | Hierarchical representation · ImageNet validation | top-1 error (%): 20.4 -> 20.3 | Helped |
| Use a hierarchical rather than flat representation for evolutionary search | Architecture search · CIFAR-10 test | error (%): 3.92 ± 0.06 -> 3.75 ± 0.12 | Helped |
| Constrain flat architectures to a parameter count similar to the hierarchical representation (ablation) | Flat evolutionary search · CIFAR-10 test | error (%): 3.92 ± 0.06 -> 4.17 ± 0.08 | Hurt |
| Increase random-search samples from 200 to 7000 | Hierarchical representation · CIFAR-10 test | error (%): 4.04 ± 0.2 -> 3.91 ± 0.15 | No clear effect |
| Increase random-search samples from 200 to 7000 | Hierarchical representation · ImageNet validation | top-1 error (%): 20.4 -> 21.0 | Hurt |
| Increase c0 from 64 to 128 | Best hierarchical evolutionary architecture · CIFAR-10 test | error (%): 3.75 ± 0.12 -> 3.63 ± 0.10 | Helped |
| Use hierarchical evolution rather than hierarchical random architecture sampling | Hierarchical representation · CIFAR-10 test | error (%): 4.21 ± 0.11 -> 3.75 ± 0.12 | Helped |
Closest papers by meaning
- Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution (ICLR 2019 · similarity 0.92)
- Building Optimal Neural Architectures using Interpretable Knowledge (CVPR 2024 · similarity 0.89)
- Towards Neural Architecture Search through Hierarchical Generative Modeling (ICML 2024 · similarity 0.89)
- Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach (CVPR 2024 · similarity 0.88)
- EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration (AAAI 2024 · similarity 0.88)
- Prior Knowledge Guided Neural Architecture Generation (ICML 2025 · 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.