进化遇见扩散：高效的神经架构生成
Evolution Meets Diffusion: Efficient Neural Architecture Generation
AI总结：
针对NAS搜索成本高及扩散式NAG全局搜索受限的问题，本文提出免训练的EDNAG，用进化算法模拟扩散去噪并由适应度引导架构分布生成，取得SOTA优化效果且推理平均提速50倍。
摘要：
神经架构搜索（NAS）因其在深度学习模型设计中的变革性潜力而受到广泛关注。然而，NAS庞大且复杂的搜索空间会带来显著的计算与时间成本。神经架构生成（NAG）通过将NAS重新表述为生成问题来解决这一点，从而能够针对特定任务精确生成最优架构。尽管前景良好，但扩散模型等主流方法在全局搜索能力方面存在局限，并且仍受高昂计算与时间需求的阻碍。为克服这些挑战，我们提出基于进化扩散的神经架构生成（EDNAG），这是一种实现高效且无需训练的架构生成的新方法。EDNAG利用进化算法模拟扩散模型中的去噪过程，使用适应度引导从随机高斯分布向最优架构分布的转变。该方法结合了进化策略与扩散模型的优势，能够快速有效地生成架构。大量实验表明，EDNAG在架构优化方面达到了最先进（SOTA）性能，准确率提升最高达10.45%。此外，它无需耗时的训练，并将推理速度平均提升50倍，展现出卓越的效率与有效性。
英文摘要：
Neural Architecture Search (NAS) has gained widespread attention for its transformative potential in deep learning model design. However, the vast and complex search space of NAS leads to significant computational and time costs. Neural Architecture Generation (NAG) addresses this by reframing NAS as a generation problem, enabling the precise generation of optimal architectures for specific tasks. Despite its promise, mainstream methods like diffusion models face limitations in global search capabilities and are still hindered by high computational and time demands. To overcome these challenges, we propose Evolutionary Diffusion-based Neural Architecture Generation (EDNAG), a novel approach that achieves efficient and training-free architecture generation. EDNAG leverages evolutionary algorithms to simulate the denoising process in diffusion models, using fitness to guide the transition from random Gaussian distributions to optimal architecture distributions. This approach combines the strengths of evolutionary strategies and diffusion models, enabling rapid and effective architecture generation. Extensive experiments demonstrate that EDNAG achieves state-of-the-art (SOTA) performance in architecture optimization, with an improvement in accuracy of up to 10.45%. Furthermore, it eliminates the need for time-consuming training and boosts inference speed by an average of 50 times, showcasing its exceptional efficiency and effectiveness.
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。
