无需环境标签，通过预测误差自动推断系统环境，提升模型泛化能力。
Environment Inference for Learning Generalizable Dynamical System
- 利用固定神经网络的预测误差动态推断环境特征，无需事先标注。
- 在无标签场景下快速收敛至真实环境划分，性能优于现有方法。
- 适用于隐私敏感或数据采集困难的大规模动态系统建模场景。
数据驱动方法为分析复杂动态系统提供了高效且稳健的解决方案，但其依赖于独立同分布（I.I.D.）数据假设，促使泛化技术的发展以应对环境差异。然而，现有技术受限于对环境标签的依赖，而这些标签在训练过程中常因数据获取困难、隐私问题及环境变化难以获得，尤其在大型公共数据集和隐私敏感领域。为此，我们提出DynaInfer，一种新方法：通过分析每轮训练中固定神经网络的预测误差，直接从数据中推断环境特征，实现无需标签的环境分配。我们证明该算法能有效解决无标签场景下的交替优化问题，并在多种动态系统上进行大量实验验证。结果表明，DynaInfer在无标签情况下显著优于现有环境分配方法，快速收敛至真实标签，且在有标签时表现更优。
原文摘要 · Abstract (English)
Data-driven methods offer efficient and robust solutions for analyzing complex dynamical systems but rely on the assumption of I.I.D. data, driving the development of generalization techniques for handling environmental differences. These techniques, however, are limited by their dependence on environment labels, which are often unavailable during training due to data acquisition challenges, privacy concerns, and environmental variability, particularly in large public datasets and privacy-sensitive domains. In response, we propose DynaInfer, a novel method that infers environment specifications by analyzing prediction errors from fixed neural networks within each training round, enabling environment assignments directly from data. We prove our algorithm effectively solves the alternating optimization problem in unlabeled scenarios and validate it through extensive experiments across diverse dynamical systems. Results show that DynaInfer outperforms existing environment assignment techniques, converges rapidly to true labels, and even achieves superior performance when environment labels are available.
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。