Right on Time: Revising Time Series Models by Constraining Their Explanations

Abstract

The reliability of deep time series models is often compromised by their tendency to rely on confounding factors, which may lead to incorrect outputs. Our newly recorded, naturally confounded dataset named P2S from a real mechanical production line emphasizes this. To avoid "Clever-Hans" moments in time series, i.e., to mitigate confounders, we introduce the method Right on Time (RioT). RioT enables, for the first time, interactions with model explanations across both the time and frequency domain. Feedback on explanations in both domains is used to steer models away from the annotated confounding factors. Dual-domain interactions are crucial to effectively address confounders in time series datasets. We empirically demonstrate that RioT can effectively guide models away from the wrong reasons in \data as well as popular time series classification and forecasting datasets.