NAS-Bench-201

NAS-Bench-201 is a benchmark dataset that contains a collection of neural architectures and their corresponding performance metrics, used to evaluate the effectiveness of neural architecture search methods.

Papers using NAS-Bench-201 (4)

GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Models2022Efficacy of Neural Prediction-Based Zero-Shot NAS2023FR-NAS: Forward-and-Reverse Graph Predictor for Efficient Neural Architecture Search2024DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation2026