AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Neural Architecture Transfer

Zhichao Lu, Gautam Sreekumar, Erik D. Goodman, Wolfgang Banzhaf, Kalyanmoy Deb, Vishnu Naresh Boddeti

TPAMI 2021 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 195 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 crossover operator to the evolutionary search (ablation)NAT evolutionary search · ImageNet, CIFAR-10, Flowers102, Stanford Carstop-1 accuracy (%)Improved
raise crossover probability (vs lowering from 0.9 to 0.2) (ablation)NAT evolutionary search · four datasetstop-1 accuracy (%)Improved
lower mutation probability (ablation)NAT evolutionary search · four datasetstop-1 accuracy (%)Improved
use low mutation index eta_m (more distant offspring) (ablation)NAT evolutionary search · four datasetstop-1 accuracy (%)Improved
adapt the supernet instead of adapting each subnet (ablation)NAT · CIFAR-10, CIFAR-100, Flowers102, STL-10top-1 accuracy (%)Improved
additional 150-epoch fine-tuning of subnets vs supernet adaptation (ablation)subnet adaptation · CIFAR-10 (4,000 per class) vs Flowers102 (20 per class)top-1 accuracy (%)Mixed
use RBF ensemble instead of standalone RBF accuracy predictor (ablation)accuracy predictor · ImageNetSpearman rank correlation: 0.705 -> 0.866Improved
use RBF ensemble instead of standalone RBF accuracy predictor (ablation)accuracy predictor · CIFAR-10Spearman rank correlation: 0.969 -> 0.959No clear effect
use NAT evolutionary search instead of random search or NSGANet (ablation)NAT pipeline · three datasets, bi-objectivehypervolume sample efficiency: 3x - 5xImproved
use reference point based selection instead of domination based selection (ablation)many-objective EA · DTLZ1 (3 to 15 objectives)IGDImproved
transfer architecture and weights with NAT instead of search on OnceForAll supernetNAT · ImageNettop-1 accuracy (%): 76.9 -> 77.5Improved
NAT-M1 vs MobileNetV3 at similar MAddsNAT-M1 · ImageNet-1Ktop-1 accuracy (%): 75.2 -> 77.5Improved

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