Research map / Architectures and efficiency / Neural architecture search
Not All Operations Contribute Equally: Hierarchical Operation-Adaptive Predictor for Neural Architecture Search
Ziye Chen, Yibing Zhan, Baosheng Yu, Mingming Gong, Bo Du
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 CGM gated fusion of layer embeddings (ablation) | HOP · NAS-Bench-101 (0.05%) | Kendall's Tau: 0.7773 -> 0.7819 | Improved |
| add CGM gated fusion of layer embeddings (ablation) | HOP · NAS-Bench-201 (1%) | Kendall's Tau: 0.7562 -> 0.7613 | Improved |
| replace CGM with mean fusion of layer embeddings (ablation) | HOP · NAS-Bench-101 (0.05%) | Kendall's Tau: 0.7819 -> 0.7704 | Hurt |
| replace CGM with mean fusion of layer embeddings (ablation) | HOP · NAS-Bench-201 (1%) | Kendall's Tau: 0.7613 -> 0.7523 | Hurt |
| increase OAM layers from 2 to 6 (ablation) | HOP · NAS-Bench-101 (0.05%) | Kendall's Tau: 0.6440 -> 0.7852 | Improved |
| increase OAM layers from 2 to 6 (ablation) | HOP · NAS-Bench-201 (1%) | Kendall's Tau: 0.5764 -> 0.7659 | Improved |
| use operation-adaptive attention (OAM) instead of GCN aggregation | GATES · NAS-Bench-101 (0.05%) | Kendall's Tau: 0.7634 -> 0.7773 | Improved |
| use operation-adaptive attention (OAM) instead of GCN aggregation | GATES · NAS-Bench-201 (1%) | Kendall's Tau: 0.7401 -> 0.7562 | Improved |
| HOP vs GATES with 0.1% training architectures | GATES · NAS-Bench-101 (0.1%) | Kendall's Tau: 0.7789 -> 0.8134 | Improved |
| HOP vs GATES with 100% training data | GATES · NAS-Bench-101 (100%) | Kendall's Tau: 0.9030 -> 0.9086 | Improved |
| HOP vs GATES with few training architectures | GATES · NAS-Bench-101 (0.05%) | N@5: 83 -> 21 | Improved |
| HOP vs GATES with 1% training architectures | GATES · NAS-Bench-201 (1%) | N@5: 19 -> 1 | Improved |
Closest papers by meaning
- A Generic Graph-Based Neural Architecture Encoding Scheme With Multifaceted Information (TPAMI 2022 · similarity 0.88)
- A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS (ECCV 2020 · similarity 0.88)
- On Redundancy and Diversity in Cell-based Neural Architecture Search (ICLR 2022 · similarity 0.87)
- Understanding Architectures Learnt by Cell-based Neural Architecture Search (ICLR 2020 · similarity 0.87)
- Towards Neural Architecture Search through Hierarchical Generative Modeling (ICML 2024 · similarity 0.85)
- einspace: Searching for Neural Architectures from Fundamental Operations (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.
