Pretraining an RL-based NAS agent on one of four Trans-NASBench-101 tasks generally improves its final performance and shortens training on another task.
In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Task Adaptation of Reinforcement Learning-based NAS Agents through Transfer Learning
Pretraining an RL-based NAS agent on one of four Trans-NASBench-101 tasks generally improves its final performance and shortens training on another task.