Learning under Temporal Label Noise

Many time series classification tasks, where labels vary over time, are affected by label noise that also varies over time. Such noise can cause label quality to improve, worsen, or periodically change over time. We first propose and formalize temporal label noise, an unstudied problem for sequential classification of time series. In this setting, multiple labels are recorded over time while being corrupted by a time-dependent noise function. We first demonstrate the importance of modeling the temporal nature of the label noise function and how existing methods will consistently underperform. We then propose methods to train noise-tolerant classifiers by estimating the temporal label noise function directly from data. We show that our methods lead to state-of-the-art performance under diverse types of temporal label noise on real-world datasets. 1 Published as a conference paper at ICLR 2025 Noise Time 0 Recon Err Temporal Ignore Noise True Static Accur Temporal Ignore Noise True Static 0 50 * Noise Rate % Time True Noise Static Methods Temporal Methods Ignore Noise 50 0 Standard supervised learning ignores label noise. Existing methods assume noise is static ignoring its temporal nature Accurately modelling the true temporal noise function, allows us to learn noise-tolerant classifiers * Best Performing * * * *