KNAS (Xu et al., 2021)

Reported on 6 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology6 results

Neural Architecture SearchonNATS-Bench Topology, CIFAR-10
Test Accuracy· 2021-11-26
93.05
best: 94.13 (RE (Real et al., 2019))
KNAS: Green Neural Architecture Search arXiv:2111.13293
Neural Architecture SearchonNATS-Bench Topology, CIFAR-100
Test Accuracy· 2021-11-26
68.91
best: 71.68 (PPO (Schulman et al., 2017))
KNAS: Green Neural Architecture Search arXiv:2111.13293
Neural Architecture SearchonNATS-Bench Topology, ImageNet16-120
Test Accuracy· 2021-11-26
34.11
best: 45.54 (EigenNas (Zhu et al., 2022))
KNAS: Green Neural Architecture Search arXiv:2111.13293
AutoMLonNATS-Bench Topology, CIFAR-10
Test Accuracy· 2021-11-26
93.05
best: 94.13 (RE (Real et al., 2019))
KNAS: Green Neural Architecture Search arXiv:2111.13293
AutoMLonNATS-Bench Topology, CIFAR-100
Test Accuracy· 2021-11-26
68.91
best: 71.68 (PPO (Schulman et al., 2017))
KNAS: Green Neural Architecture Search arXiv:2111.13293
AutoMLonNATS-Bench Topology, ImageNet16-120
Test Accuracy· 2021-11-26
34.11
best: 45.54 (EigenNas (Zhu et al., 2022))
KNAS: Green Neural Architecture Search arXiv:2111.13293