突破传统神经网络搜索的拓扑限制，实现更灵活的自动架构设计。
FX-DARTS: Designing Topology-unconstrained Architectures with Differentiable Architecture Search and Entropy-based Super-network Shrinking
- 采用基于熵的超网络剪枝机制，解除细胞结构固定约束。
- 单次搜索即生成性能与计算量平衡的多种高效架构。
- 适合追求架构灵活性和自动化设计的深度学习研究者。
现有可微分架构搜索（DARTS）方法对搜索空间施加强先验，如同一类型单元共享相同拓扑结构，且每个中间节点仅保留来自不同节点的两个操作符。这些先验虽降低优化难度并提升可应用性，却限制了自动化机器学习（Auto-ML）发展，阻碍算法探索更具表现力的神经网络。本文提出柔性可微架构搜索（FX-DARTS），通过消除拓扑结构约束并改进超网络离散化机制，结合基于熵的超网络剪枝（ESS）框架，解决由此带来的挑战。结果表明，FX-DARTS可在无严格先验条件下稳定生成多样化架构，且在图像分类基准上实现单次搜索即获得性能与复杂度良好权衡的模型。
原文摘要 · Abstract (English)
Strong priors are imposed on the search space of Differentiable Architecture Search (DARTS), such that cells of the same type share the same topological structure and each intermediate node retains two operators from distinct nodes. While these priors reduce optimization difficulties and improve the applicability of searched architectures, they hinder the subsequent development of automated machine learning (Auto-ML) and prevent the optimization algorithm from exploring more powerful neural networks through improved architectural flexibility. This paper aims to reduce these prior constraints by eliminating restrictions on cell topology and modifying the discretization mechanism for super-networks. Specifically, the Flexible DARTS (FX-DARTS) method, which leverages an Entropy-based Super-Network Shrinking (ESS) framework, is presented to address the challenges arising from the elimination of prior constraints. Notably, FX-DARTS enables the derivation of neural architectures without strict prior rules while maintaining the stability in the enlarged search space. Experimental results on image classification benchmarks demonstrate that FX-DARTS is capable of exploring a set of neural architectures with competitive trade-offs between performance and computational complexity within a single search procedure.
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。