We introduce Universal Neural Architecture Space (UniNAS), a generic search space for neural architecture search (NAS) which unifies convolutional networks, transformers, and their hybrid architectures under a single, flexible framework. Our approach enables discovery of novel architectures as well as analyzing existing architectures in a common framework. We also propose a new search algorithm that allows traversing the proposed search space, and demonstrate that the space contains interesting architectures, which, when using identical training setup, outperform state-of-the-art hand-crafted architectures. Finally, a unified toolkit including a standardized training and evaluation protocol is introduced to foster reproducibility and enable fair comparison in NAS research. Overall, this work opens a pathway towards systematically exploring the full spectrum of neural architectures with a unified graph-based NAS perspective.

翻译：本文提出通用神经架构空间（UniNAS），这是一个用于神经架构搜索（NAS）的通用搜索空间，将卷积网络、Transformer及其混合架构统一在单一灵活框架下。我们的方法既能发现新颖架构，也能在统一框架中分析现有架构。我们还提出一种新的搜索算法，可在该搜索空间中进行遍历，并证明该空间包含的架构在相同训练设置下能超越当前最优手工设计架构。最后，我们开发了包含标准化训练与评估协议的统一工具包，以提升NAS研究的可复现性并实现公平比较。总体而言，本研究通过基于图的统一NAS视角，为系统探索神经架构全谱系开辟了新路径。