Research map / Architectures and efficiency / Neural architecture search
Revisiting Parameter Sharing for Automatic Neural Channel Number Search
Jiaxing Wang, Haoli Bai, Jiaxiang Wu, Xupeng Shi, Junzhou Huang, Irwin King, Michael Lyu, Jian Cheng
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 |
|---|---|---|---|
| anneal sharing level (transitionary) instead of fixed ordinal sharing (ablation) | APS channel search ResNet-20 · CIFAR-10 | accuracy: 91.61% -> 92.02% | Improved |
| anneal sharing level (transitionary) instead of fixed independent sharing (ablation) | APS channel search ResNet-20 · CIFAR-10 | accuracy: 91.24% -> 92.02% | Improved |
| transitionary instead of ordinal sharing (ablation) | APS channel search ResNet-56 · CIFAR-10 | accuracy: 92.93% -> 93.42% | Improved |
| transitionary instead of independent sharing (ablation) | APS channel search ResNet-56 · CIFAR-10 | accuracy: 92.85% -> 93.42% | Improved |
| transitionary instead of ordinal sharing (ablation) | APS ResNet-18 · ImageNet | top-1 accuracy: 68.60% -> 69.34% | Improved |
| transitionary instead of independent sharing (ablation) | APS MobileNet-V2 · ImageNet | top-1 accuracy: 72.38% -> 72.83% | Improved |
| higher sharing level (ordinal vs independent) speeds early accuracy rise (ablation) | APS channel search ResNet-20 · CIFAR-10 warm-up | training accuracy speed | Improved |
| higher sharing level (ordinal) on architecture discrimination (ablation) | APS channel search ResNet-20 · CIFAR-10 | controller discrimination | Hurt |
| transition learning rate tau too large (1e-1) vs 1e-3 (ablation) | APS-T · CIFAR-10 ResNet-20 | accuracy/discrimination: Phi 2.78e4 (1e-1) vs 2.70e2 (1e-3) | Hurt |
| search at 100% FLOPs with APS-T vs original network | ResNet-20 · CIFAR-10 | accuracy: 92.78% -> 93.14% | Improved |
Closest papers by meaning
- Neural Parameter Allocation Search (ICLR 2022 · similarity 0.86)
- Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNAS (CVPR 2020 · similarity 0.86)
- AOWS: Adaptive and Optimal Network Width Search With Latency Constraints (CVPR 2020 · similarity 0.86)
- Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS (NeurIPS 2020 · similarity 0.86)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.84)
- Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach (CVPR 2024 · similarity 0.83)
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.
