发表机构
Unitec Institute of Technology; University of Canterbury; University of Otago; Auckland University of Technology; The Alan Turing Institute; University College London（Unitec理工学院; 坎特伯雷大学; 奥塔哥大学; 奥克兰理工大学; 艾伦·图灵研究所; 伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对时间序列预测中极端值干扰集成效果的问题，提出CAGE框架，融合生成模型、对抗判别与保形预测，动态调整权重，提升预测可靠性与准确性，并在牛奶收集和猴痘数据集上验证其优于传统方法。
AI 中文摘要
准确的时间序列预测在多个领域至关重要，然而传统的集成方法常常受到极端预测不成比例影响的困扰。我们引入了保形对抗生成集成（CAGE），这是一个新颖的框架，结合了生成建模、对抗判别和保形预测，以增强预测的可靠性和准确性。CAGE采用多个生成模型产生初始预测，然后由判别组件使用保形预测技术进行评估。从非一致性得分得出的p值有助于动态调整模型权重，最小化不可靠预测的影响。这种方法确保只有最可信的预测对最终集成输出做出贡献。我们对新西兰牛奶收集的时间序列数据和来自公共owid-monkeypox数据集的全球健康数据的实证和统计分析表明，CAGE优于传统集成方法，特别是在处理异常值和噪声数据方面。通过整合保形预测，CAGE提供了准确且统计严谨的预测，增强了决策制定。我们特意在两个不同的数据集上展示了性能，以表明所提出的方法提供了一种可能在金融、天气和供应链管理中适用的多功能解决方案。
英文摘要
Accurate time series forecasting is critical across various domains, yet traditional ensemble methods often suffer from the disproportionate influence of extreme forecasts. We introduce the Conformal Adversarial Generative Ensemble (CAGE), a novel framework that combines generative modeling, adversarial discrimination, and conformal prediction to enhance forecast reliability and accuracy. CAGE employs multiple generative models to produce initial forecasts, which are then evaluated by a discriminative component using conformal prediction techniques. P-values derived from nonconformity scores help dynamically adjust model weights, minimizing the impact of unreliable forecasts. This approach ensures that only the most credible predictions contribute to the final ensemble output. Our empirical and statistical analyses of time series data from New Zealand's milk collection and the global health data from the public owid-monkeypox dataset show that the CAGE outperforms traditional ensemble methods, especially in handling outliers and noisy data. By incorporating conformal prediction, CAGE delivers accurate and statistically rigorous forecasts, enhancing decision-making. We have demonstrated performance on two different datasets deliberately to showcase that the proposed method offers a versatile solution potentially applicable across finance, weather, and supply chain management.
CommentsPublished in ICONIP 2024 (Neural Information Processing), LNCS 15287, Springer Nature, 2025
Journal refNeural Information Processing (ICONIP 2024), Lecture Notes in Computer Science (LNCS), vol. 15287, pp. 135-150, Springer, 2025
DOI：10.1007/978-981-96-6579-2_10
