AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Bridge the Gap Between Architecture Spaces via A Cross-Domain Predictor

Yuqiao Liu, Yehui Tang, Zeqiong Lv, Yunhe Wang, Yanan Sun

NeurIPS 2022 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 2 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 progressive subspace partition (cosine schedule) vs none (ablation)CDP · shallow DARTSKTau: 0.3650 -> 0.5176Improved
cosine vs linear subspace increase schedule (ablation)CDP · shallow DARTSKTau: 0.4949 -> 0.5176Improved
linear progressive schedule vs none (ablation)CDP · shallow DARTSKTau: 0.3650 -> 0.4949Improved
add small assistant space (ablation)CDP · shallow DARTSKTau: 0.5176 -> 0.5051Hurt
add medium assistant space (tiny DARTS) (ablation)CDP · shallow DARTSKTau: 0.5176 -> 0.5306Improved
LMMD instead of MMD (ablation)CDP · shallow DARTSKTau: 0.4549 -> 0.4969Improved
LMMD + PSP instead of LMMD alone (ablation)CDP · shallow DARTSKTau: 0.4969 -> 0.5306Improved
LMMD + PSP instead of DANN (ablation)CDP · shallow DARTSKTau: 0.4686 -> 0.5306Improved
LMMD + PSP instead of CORAL (ablation)CDP · shallow DARTSKTau: 0.4306 -> 0.5306Improved
CDP vs PC-DARTS at similar search costCDP · ImageNettop-1 accuracy: 74.9 -> 76.9Improved
CDP vs DARTS on CIFAR-10CDP · CIFAR-10accuracy: 97.24 ± 0.09 -> 97.51Improved
CDP vs WeakNAS on ImageNet top-5CDP · ImageNettop-5 accuracy: 93.2 -> 93.0No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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