AI 中文总结
本文针对神经集成搜索（NES）计算成本高的问题，提出双目标代理引导的集成搜索方法，在多个数据集上取得优于或相当于基线的性能。
AI 中文摘要
集成是提升深度神经网络性能与鲁棒性的标准方式，但其有效性关键取决于单个模型的质量与多样性。多数神经架构搜索（NAS）方法计算成本高昂，将其扩展至需联合优化单个架构与集成组成的神经集成搜索（NES）时，搜索空间呈指数级增长，导致问题在计算上难以处理。为解决该问题，本文提出双目标代理引导的集成搜索：将候选架构表示为有向无环图，独立训练两个代理模型以估计预测准确率与多样性潜力，二者的联合估计引导NES框架高效识别既具个体优势又具集体多样性的架构。最终集成在FashionMNIST、CIFAR-10和CIFAR-100数据集上，取得与Deep Ensembles、Random Search等标准基线相当或更优的性能。
英文摘要
Ensembles are a standard way to improve the performance and robustness of deep neural networks, but their effectiveness crucially depends on both the quality and the diversity of individual models. Most neural architecture search (NAS) methods are computationally expensive. Extending them to neural ensemble search (NES), which requires joint optimization of individual architectures and their ensemble composition, leads to an exponential growth of the search space and makes the problem computationally intractable. To address this, we introduce a dual-objective surrogate-guided ensemble search: candidate architectures are represented as directed acyclic graphs, and two surrogate models are trained independently to estimate predictive accuracy and diversity potential. Their combined estimates guide an NES framework that efficiently identifies architectures that are both individually strong and collectively diverse. Our final ensemble achieves competitive or superior performance compared to standard baselines such as Deep Ensembles and Random Search on FashionMNIST, CIFAR-10, and CIFAR-100.
CommentsThe paper was presented at the "Artificial Intelligence Applications and Innovations 2026" conference. The final publication is available at https://link.springer.com/chapter/10.1007/978-3-032-30612-8_12
Journal refIFIP Advances in Information and Communication Technology, vol 792. Springer, Cham. 2027
DOI：10.1007/978-3-032-30612-8_12
