
Neural graph features (GRAF) provide fast and interpretable performance prediction that outperforms zero-cost proxies and other common encodings. The combination of GRAF and zero-cost proxies achieves the best performance at a fraction of the cost.


coremsg

interpretable-neural-graph-features-outperform-zero-cost-proxies-for-efficient-performance-prediction-in-neural-architecture-search


Interpretable Neural Graph Features Outperform Zero-Cost Proxies for Efficient Performance Prediction in Neural Architecture Search


title_rewrite


A novel graph-based performance predictor that leverages both forward and reverse representations of neural architectures to enhance prediction accuracy, especially in data-limited settings.


efficient-neural-architecture-search-using-a-forward-and-reverse-graph-predictor


Efficient Neural Architecture Search Using a Forward-and-Reverse Graph Predictor
