Neural Architecture Search On Nas Bench 201

评估指标

Accuracy (Test)
Accuracy (Val)
Search time (s)

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
CR-LSO46.9846.51-CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
Shapley-NAS46.8546.57-Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search
β-RDARTS-L246.71--$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
β-SDARTS-RS46.71--$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
NAR46.6646.16-Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search
BaLeNAS-TF46.5446.14-BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule-
AG-Net46.4246.73-Learning Where To Look -- Generative NAS is Surprisingly Efficient
Local search46.38-151200Exploring the Loss Landscape in Neural Architecture Search
NASBOT46.37-75600Neural Architecture Search with Bayesian Optimisation and Optimal Transport
GAEA DARTS (ERM)46.36--Geometry-Aware Gradient Algorithms for Neural Architecture Search
ParZC46.3446.37-ParZC: Parametric Zero-Cost Proxies for Efficient NAS-
α-DARTS46.3446.17-$α$ DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling-
Λ-DARTS46.3446.37-$Λ$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells
DrNAS46.3446.37-DrNAS: Dirichlet Neural Architecture Search
β-DARTS46.3446.37-$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
IS-DARTS 46.34 46.37-IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance
TNAS46.31--When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search
BANANAS46.3-100800BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search
arch2vec46.27--Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
RF-DARTS46.146.40-Differentiable Architecture Search with Random Features-
0 of 49 row(s) selected.
Neural Architecture Search On Nas Bench 201 | SOTA | HyperAI超神经