发表机构
Orange Research; AgroParisTech（奥朗日研究中心; 巴黎高等农业工程师学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对非平稳环境下的时间序列早期分类问题，提出基于强化学习的DQeND端到端架构，联合学习表示、分类与触发决策，其鲁棒性和性能优于可分离基线，验证了端到端学习的优势。
AI 中文摘要
时间序列早期分类（Early Classification of Time Series, ECTS）需要在本质上是在线且不断演变的环境中尽早做出准确决策。然而，大多数现有方法假设环境是平稳的，且依赖于可分离的设计，其中分类和触发机制是独立优化的，这一假设从根本上限制了它们在数据分布漂移下的适应性。在本研究中，我们挑战这一范式，研究非平稳条件下的ECTS问题。我们在受控漂移场景下，首次对可分离方法和端到端方法进行了系统比较。基于强化学习，我们提出了DQeND这一统一架构，该架构联合学习表示、分类和触发决策，同时可与最先进的可分离基线直接比较。在广泛的漂移场景中，DQeND在各种非平稳场景下表现出强鲁棒性，始终优于可分离基线。消融研究进一步表明，联合更新表示和决策模块对这些性能提升至关重要。总体而言，我们的结果表明，端到端学习可为动态环境中的ECTS提供更强的适应能力，并推动对可分离设计替代方案的进一步研究。
英文摘要
Early Classification of Time Series (ECTS) requires making accurate decisions as early as possible in inherently online and evolving environments. Yet, most existing methods assume stationarity and rely on separable designs, where classification and triggering are optimized independently, an assumption that fundamentally limits their adaptability under drift. In this work, we challenge this paradigm and study ECTS under non-stationary conditions. We provide the first systematic comparison between separable and end-to-end approaches across controlled drifting scenarios. Building on Reinforcement Learning, we introduce DQeND, a unified architecture that jointly learns representation, classification, and triggering decisions, while remaining directly comparable to state-of-the-art separable baselines. Across a wide range of drifts, DQeND demonstrates strong robustness across various non-stationary scenarios, consistently outperforming separable baselines. An ablation study further highlights that jointly updating representation and decision modules is critical to these gains. Overall, our results indicate that end-to-end learning can offer improved adaptation capabilities for ECTS in dynamic environments, and motivate further investigation of alternatives to separable designs.
