AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning

Xiawu Zheng, Chenyi Yang, Shaokun Zhang, Yan Wang, Baochang Zhang, Yongjian Wu, Yunsheng Wu, Ling Shao, Rongrong Ji

IJCV 2023 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 38 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
add dynamic operator pruning during search (ablation)DDPNAS · CIFAR-10test error (%): 2.75 -> 2.59Improved
add dynamic operator pruning during search (ablation)DDPNAS · CIFAR-10search cost (GPU days): 0.25 -> 0.075Improved
add dynamic pruning (ablation)DDPNAS · GLUE devaverage score: 79.2 -> 80.4Improved
pruning step between 2 and 4 (ablation)DDPNAS · CIFAR-10test error (%)Improved
pruning step larger than 4 (ablation)DDPNAS · CIFAR-10test error (%)Hurt
change gamma within [0.7, 0.9] (ablation)DDPNAS · CIFAR-10test error (%)No clear effect
constrain network to N = 4 non-parameter ops instead of N = 2 (ablation)DDPNAS · CIFAR-10test error (%): 2.72 -> 2.59Mixed
constrain height H = 1 with N = 4 (ablation)DDPNAS · CIFAR-10test error (%): 2.59 -> 2.93Hurt
use DDPNAS over LayerDrop at 67MBERT compression · GLUE dev (RTE)accuracy: 65.2 -> 69.3Improved
use DDPNAS over LayerDrop at 67MBERT compression · GLUE dev (CoLA)Matthews corr.: 45.4 -> 54.1Improved
transfer DDPNAS backbone vs ESPNetV2semantic segmentation · CityscapesmIoU (%): 62.1 -> 71.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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