NAS-Bench-101
Emerging4papers using it
2022first seen
NAS-Bench-101 is a benchmark dataset that contains a fixed set of neural architectures and their corresponding performance metrics, used to evaluate neural architecture search (NAS) methods.
Papers using NAS-Bench-101 (4)
- Encodings for Prediction-based Neural Architecture SearchGraphPNAS: Learning Distribution of Good Neural Architectures via Deep
Graph Generative ModelsFR-NAS: Forward-and-Reverse Graph Predictor for Efficient Neural
Architecture SearchDGPO: RL-Steered Graph Diffusion for Neural Architecture Generation