用代理模型加速神经网络集成搜索，兼顾模型强弱与多样性。
Surrogate assisted diversity estimation in neural ensemble search
- 用两个独立代理模型分别预测准确率和多样性潜力
- 在三个数据集上性能优于或媲美主流基线方法
- 适合需要高效构建高性能集成模型的研究者
集成模型是提升深度神经网络性能与鲁棒性的常用方法，其效果关键取决于个体模型的质量与多样性。现有神经架构搜索（NAS）方法计算成本高，将其扩展至神经集成搜索（NES）会带来搜索空间指数级增长，导致计算不可行。为此，我们提出一种双目标代理引导的集成搜索框架：候选架构以有向无环图表示，训练两个独立的代理模型分别估计预测准确率和多样性潜力，其联合估计指导集成搜索，高效发现既个体优秀又集体多样化的架构。最终集成在FashionMNIST、CIFAR-10和CIFAR-100上表现优于或媲美标准基线（如Deep Ensembles和Random Search）。
原文摘要 · Abstract (English)
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.
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。