DANCE让神经网络架构能自动适应不同硬件，省时省力还稳定
DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation
- 把架构搜索转为连续进化，用概率分布动态调整网络结构
- 在5个数据集上精度超现有方法，搜索成本大幅降低
- 适合资源受限场景，尤其适合需要多设备部署的开发者
神经架构搜索（NAS）已成为自动化设计神经网络的强大工具。然而，现有方法在实际部署中面临关键挑战：架构缺乏跨场景适应能力，每个部署环境需独立耗时搜索，且在不同平台上的性能一致性难以保证。我们提出DANCE（动态架构的神经连续演化），将架构搜索重构为连续演化问题，通过学习架构组件的概率分布实现平滑适应。DANCE引入三项核心创新：连续架构分布支持平滑调整，统一架构空间结合可学习选择门实现高效采样，多阶段训练策略优化部署表现。在五个数据集上的大量实验表明，DANCE在保持高精度的同时显著降低搜索成本。在不同计算约束下，模型性能稳定，能无缝适配各类硬件需求。代码与附录见https://github.com/Applied-Machine-Learning-Lab/DANCE。
原文摘要 · Abstract (English)
Neural Architecture Search (NAS) has emerged as a powerful approach for automating neural network design. However, existing NAS methods face critical limitations in real-world deployments: architectures lack adaptability across scenarios, each deployment context requires costly separate searches, and performance consistency across diverse platforms remains challenging. We propose DANCE (Dynamic Architectures with Neural Continuous Evolution), which reformulates architecture search as a continuous evolution problem through learning distributions over architectural components. DANCE introduces three key innovations: a continuous architecture distribution enabling smooth adaptation, a unified architecture space with learned selection gates for efficient sampling, and a multi-stage training strategy for effective deployment optimization. Extensive experiments across five datasets demonstrate DANCE's effectiveness. Our method consistently outperforms state-of-the-art NAS approaches in terms of accuracy while significantly reducing search costs. Under varying computational constraints, DANCE maintains robust performance while smoothly adapting architectures to different hardware requirements. The code and appendix can be found at https://github.com/Applied-Machine-Learning-Lab/DANCE.
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。