Neural Architecture Search On Nas Bench 201 1

评估指标

Accuracy (Test)

Accuracy (Val)

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
Shapley-NAS	94.37	91.61	Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search
AG-Net	94.37	91.61	Learning Where To Look -- Generative NAS is Surprisingly Efficient
DiNAS	94.37	91.61	Multi-conditioned Graph Diffusion for Neural Architecture Search
β-DARTS	94.36	91.55	$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
Λ-DARTS	94.36	91.55	$Λ$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells
IS-DARTS	94.36	91.55	IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance
DrNAS	94.36	91.55	DrNAS: Dirichlet Neural Architecture Search
CR-LSO	94.35	91.54	CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
TNAS	94.35	-	When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search
NAR	94.33	91.44	Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search
BaLeNAS-TF	94.33	91.52	BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule	-
α-DARTS	94.3	91.49	$α$ DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling	-
RF-DARTS	94.27	91.3	Differentiable Architecture Search with Random Features	-
arch2vec	94.18	91.41	Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
GenNAS	94.18	-	Generic Neural Architecture Search via Regression
GAEA DARTS (ERM)	94.1	-	Geometry-Aware Gradient Algorithms for Neural Architecture Search
PRE-NAS	94.04	91.37	PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search	-
CDARTS	94.02	91.12	Cyclic Differentiable Architecture Search
GAE	93.99	91.26	Guided Evolutionary Neural Architecture Search With Efficient Performance Estimation	-
DU-DARTS	93.86	91.21	DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search	-

0 of 37 row(s) selected.