The reliability of deep time series models is often compromised by their tendency to rely on confounding factors, which may lead to misleading results. Our newly recorded, naturally confounded dataset named P2S from a real mechanical production line emphasizes this. To tackle the challenging problem of mitigating confounders in time series data, we introduce Right on Time (RioT). Our method enables interactions with model explanations across both the time and frequency domain. Feedback on explanations in both domains is then used to constrain the model, steering it away from the annotated confounding factors. The dual-domain interaction strategy is crucial for effectively addressing confounders in time series datasets. We empirically demonstrate that RioT can effectively guide models away from the wrong reasons in P2S as well as popular time series classification and forecasting datasets.

翻译：深度时间序列模型的可靠性常因其对混杂因素的依赖而受损，这可能导致误导性结果。我们从一个真实机械生产线新录制的自然混杂数据集P2S充分印证了这一点。为解决时间序列数据中缓解混杂因素这一难题，我们提出了“准时无误”（RioT）方法。该方法支持在时域和频域两个维度上与模型解释进行交互。两个域中的解释反馈被用于约束模型，使其偏离已标注的混杂因素。这种双域交互策略对于有效处理时间序列数据集中的混杂因素至关重要。我们通过实验证明，RioT能有效引导模型在P2S数据集以及流行的时序分类与预测数据集中避免依赖错误的特征。