SuperFast: Fast Supernet Training Using Initial Knowledge

Abstract

Once-for-all based neural architecture search (NAS) proposes to train a supernet once and extract specialized subnets from it for efficient deployment. This decoupling between training and search enables easy multi-target deployment without retraining. Nevertheless, the initial training cost has remained extremely high, with SOTA approaches like ElasticViT and NASViT taking more than 72 and 83 GPU days respectively. While other approaches have tried to accelerate the training by warming up the largest model in the search space, we argue that this is suboptimal, and knowledge is easier scaled upward than downward. Hence, we propose SuperFast, a simple, plug and play workflow, that (I.) pretrains a subnet of the supernet search space, and (II.) distributes its knowledge within the supernet before the training. SuperFast offers a substantial acceleration in the supernet training, resulting in a significantly better accuracy vs. training-cost trade-off. Using SuperFast on both ElasticViT and NASViT supernets achieves the baseline’s accuracy 1.4× and 1.8× faster on the ImageNet dataset. Moreover, for a given time budget, SuperFast improves accuracy vs. latency trade-offs for subnets, gaining 4.0 p.p. for the 20−50 ms range on Pixel 6. Code available in https://github.com/MoritzTho/SuperFast.