AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Topology-Weighted Effective Rank: A Zero-Cost Proxy for Training Dynamics Stability in Neural Architecture Search

Haojie Zhang, Yeming Yang, Songbai Liu, Lijia Ma, Ka-Chun Wong, Qiuzhen Lin

ECCV 2026 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 0 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
integrate ER-Score into the Auto-Prox search frameworkAuto-Prox · ViT-Bench-101 C100 (AutoFormer space)Spearman correlation (%): 63.87 -> 95.36Improved
integrate ER-Score into the Auto-Prox search frameworkAuto-Prox · ViT-Bench-101 Flowers (AutoFormer space)Spearman correlation (%): 83.65 -> 89.17Improved
integrate ER-Score into the Auto-Prox search frameworkAuto-Prox · ViT-Bench-101 Chaoyang (AutoFormer space)Spearman correlation (%): 41.76 -> 53.58Improved
integrate ER-Score into the Auto-Prox search frameworkAuto-Prox · ViT-Bench-101 C100 (PiT space)Spearman correlation (%): 95.12 -> 95.90Improved
integrate ER-Score into the Auto-Prox search frameworkAuto-Prox · ViT-Bench-101 Flowers (PiT space)Spearman correlation (%): 92.94 -> 96.33Improved
integrate ER-Score into the Auto-Prox search frameworkAuto-Prox · ViT-Bench-101 Chaoyang (PiT space)Spearman correlation (%): 55.09 -> 76.14Improved
add topology weighting (PageRank) to ER-Score, giving TER-Score (ablation)ER-Score · NAS-Bench-301 elite architecture nDCGnDCGImproved
add degree or PageRank topology weighting to ER-Score (ablation)ER-Score · NAS-Bench-201/301, TransNAS-Bench-101Spearman correlationImproved
use Gaussian or uniform random inputs instead of real images for the mini-batch (ablation)ER-Score and TER-Score · Mini-batch distribution ablationSpearman correlationImproved
use all-one input instead of random input (ablation)ER-Score and TER-Score · Mini-batch distribution ablationSpearman correlationHurt
use medium input resolution instead of low or high resolution (ablation)ER-Score and TER-Score · Mini-batch resolution ablationSpearman correlationImproved
use TER-Score as the guidance signal in evolutionary search instead of other ZCPsEvolutionary search · NAS-Bench-301 surrogate (DARTS space)predicted accuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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