CATCH：基于上下文的Meta强化学习可迁移体系结构搜索
CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
摘要：
近年来，神经网络结构搜索（NAS）取得了许多突破性进展。尽管它取得了显著的进步，但许多算法都局限于特定的搜索空间。他们也缺乏有效的机制，在面对多个任务时重用知识。这些挑战排除了它们的适用性，并促使我们提出CATCH，一种新的基于上下文的Meta强化学习（RL）算法的可转移架构搜索。元学习和RL的结合使CATCH能够有效地适应新任务，同时对搜索空间不可知。CATCH利用概率编码器将任务属性编码为潜在上下文变量，然后引导CATCH的控制器快速“捕获”性能最好的网络。上下文还帮助网络评估器过滤劣质候选者并加速学习。大量的实验表明CATCH的普遍性和搜索效率超过许多其他广泛认可的算法。它还能够处理跨域架构搜索，因为ImageNet，COCO和Cityscapes上的竞争网络已被识别。据我们所知，这是第一个提出高效可转移NAS解决方案的工作，同时在各种设置中保持鲁棒性。
英文摘要：
Neural Architecture Search (NAS) achieved many breakthroughs in recent years. In spite of its remarkable progress, many algorithms are restricted to particular search spaces. They also lack efficient mechanisms to reuse knowledge when confronting multiple tasks. These challenges preclude their applicability, and motivate our proposal of CATCH, a novel Context-bAsed meTa reinforcement learning (RL) algorithm for transferrable arChitecture searcH. The combination of meta-learning and RL allows CATCH to efficiently adapt to new tasks while being agnostic to search spaces. CATCH utilizes a probabilistic encoder to encode task properties into latent context variables, which then guide CATCH's controller to quickly "catch" top-performing networks. The contexts also assist a network evaluator in filtering inferior candidates and speed up learning. Extensive experiments demonstrate CATCH's universality and search efficiency over many other widely-recognized algorithms. It is also capable of handling cross-domain architecture search as competitive networks on ImageNet, COCO, and Cityscapes are identified. This is the first work to our knowledge that proposes an efficient transferrable NAS solution while maintaining robustness across various settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
