用迁移学习提升强化学习型神经网络架构搜索的效率与性能。
Task Adaptation of Reinforcement Learning-based NAS Agents through Transfer Learning
- 在不同任务间迁移预训练的强化学习搜索代理。
- 迁移后模型最终性能在90%以上任务中得到提升，训练时间显著缩短。
- 适用于需要快速部署NAS代理的研究者和工业界应用。
近期提出了一种基于强化学习的神经网络架构搜索（NAS）新范式，聚焦于对已有架构的增量优化。本文评估了此类强化学习代理在不同任务间的迁移能力。实验基于Trans-NASBench-101基准，考察迁移代理的有效性及其训练速度。结果表明，在除1个任务外的所有任务中，先在某一任务上预训练的代理在另一任务上的最终性能均有所提升。同时，通过跨任务预训练可显著缩短代理的训练时间。这些效果在不同源任务与目标任务间均成立，尽管部分任务间迁移效果更明显。研究证实，迁移学习可有效降低基于强化学习的NAS代理初始训练的计算成本。
原文摘要 · Abstract (English)
Recently, a novel paradigm has been proposed for reinforcement learning-based NAS agents, that revolves around the incremental improvement of a given architecture. We assess the abilities of such reinforcement learning agents to transfer between different tasks. We perform our evaluation using the Trans-NASBench-101 benchmark, and consider the efficacy of the transferred agents, as well as how quickly they can be trained. We find that pretraining an agent on one task benefits the performance of the agent in another task in all but 1 task when considering final performance. We also show that the training procedure for an agent can be shortened significantly by pretraining it on another task. Our results indicate that these effects occur regardless of the source or target task, although they are more pronounced for some tasks than for others. Our results show that transfer learning can be an effective tool in mitigating the computational cost of the initial training procedure for reinforcement learning-based NAS agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。