AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Dependency-aware Differentiable Neural Architecture Search

Buang Zhang, Xinle Wu, Hao Miao, Bin Yang, Chenjuan Guo

ECCV 2024 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
model dependencies between edges with a multivariate normal architecture distributionDARTS · NAS-Bench-201accuracy (%): 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-201accuracy over search timeImproved
learn no dependencies (diagonal matrix, equal to vanilla DARTS) (ablation)DaNAS · NAS-Bench-201accuracy over search timeHurt
mask 30% or 60% of dependency matrix entries (ablation)DaNAS · NAS-Bench-201accuracy over search timeHurt
add dependency-aware search space pruning (ablation)DaNAS · NAS-Bench-201accuracy (%): 94.25 -> 94.33Improved
use dependency modeling with P-DARTS style pruning versus dependency-aware pruning (ablation)DaNAS · NAS-Bench-201accuracy (%): 92.08 -> 94.33Improved
apply DaNAS on the DARTS search space against PC-DARTS and SGASCIFAR-10 · DARTS space, CIFAR-10test error (%): 2.57 -> 2.53 (vs PC-DARTS)Improved
transfer DaNAS cell to ImageNetDaNAS · ImageNettop-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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy