Research map / Architectures and efficiency / Neural architecture search
Dependency-aware Differentiable Neural Architecture Search
Buang Zhang, Xinle Wu, Hao Miao, Bin Yang, Chenjuan Guo
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 |
|---|---|---|---|
| model dependencies between edges with a multivariate normal architecture distribution | DARTS · NAS-Bench-201 | accuracy (%): 54.30 -> 94.33 on CIFAR-10 versus DARTS(2nd) | Improved |
| learn the full dependency matrix instead of masked or diagonal matrices (ablation) | DaNAS · NAS-Bench-201 | accuracy over search time | Improved |
| learn no dependencies (diagonal matrix, equal to vanilla DARTS) (ablation) | DaNAS · NAS-Bench-201 | accuracy over search time | Hurt |
| mask 30% or 60% of dependency matrix entries (ablation) | DaNAS · NAS-Bench-201 | accuracy over search time | Hurt |
| add dependency-aware search space pruning (ablation) | DaNAS · NAS-Bench-201 | accuracy (%): 94.25 -> 94.33 | Improved |
| use dependency modeling with P-DARTS style pruning versus dependency-aware pruning (ablation) | DaNAS · NAS-Bench-201 | accuracy (%): 92.08 -> 94.33 | Improved |
| apply DaNAS on the DARTS search space against PC-DARTS and SGAS | CIFAR-10 · DARTS space, CIFAR-10 | test error (%): 2.57 -> 2.53 (vs PC-DARTS) | Improved |
| transfer DaNAS cell to ImageNet | DaNAS · ImageNet | top-1 error (%): 24.44 -> 24.21 (vs SGAS) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DARTS- — DARTS-: Robustly Stepping out of Performance Collapse Without Indicators (ICLR 2021) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients (ICML 2021 · similarity 0.93)
- BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule (CVPR 2022 · similarity 0.92)
- Rethinking Architecture Selection in Differentiable NAS (ICLR 2021 · similarity 0.92)
- Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild (IJCV 2020 · similarity 0.91)
- EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration (AAAI 2024 · similarity 0.90)
- $\beta $-DARTS++: Bi-Level Regularization for Proxy-Robust Differentiable Architecture Search (TPAMI 2025 · similarity 0.90)
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.
