Extreme events frequently occur in real-world time series and often carry significant practical implications. In domains such as climate and healthcare, these events, such as floods, heatwaves, or acute medical episodes, can lead to serious consequences. Accurate forecasting of such events is therefore of substantial importance. Most existing time series forecasting models are optimized for overall performance within the prediction window, but often struggle to accurately predict extreme events, such as high temperatures or heart rate spikes. The main challenges are data imbalance and the neglect of valuable information contained in intermediate events that precede extreme events. In this paper, we propose xTime, a novel framework for extreme event forecasting in time series. xTime leverages knowledge distillation to transfer information from models trained on lower-rarity events, thereby improving prediction performance on rarer ones. In addition, we introduce a mixture of experts (MoE) mechanism that dynamically selects and fuses outputs from expert models across different rarity levels, which further improves the forecasting performance for extreme events. Experiments on multiple datasets show that xTime achieves consistent improvements, with forecasting accuracy on extreme events improving from 3% to 78%.

翻译：极端事件在现实世界的时间序列中频繁发生，且往往具有重要的实际意义。在气候和医疗等领域，诸如洪水、热浪或急性医疗事件等极端事件可能导致严重后果。因此，对此类事件进行准确预测至关重要。现有的大多数时间序列预测模型主要针对预测窗口内的整体性能进行优化，但在准确预测极端事件（如高温或心率骤升）方面往往表现不佳。主要挑战在于数据不平衡，以及忽视了极端事件发生前中间事件所包含的宝贵信息。本文提出 xTime，一种用于时间序列极端事件预测的新颖框架。xTime 利用知识蒸馏技术，从训练于较低稀有度事件的模型中迁移信息，从而提升对更稀有事件的预测性能。此外，我们引入了一种专家混合（MoE）机制，该机制能动态选择和融合来自不同稀有度级别的专家模型的输出，进一步提升了极端事件的预测性能。在多个数据集上的实验表明，xTime 取得了持续的改进，极端事件的预测准确率提升了 3% 至 78%。