EarlyMix: Hierarchical Mixing for Early Time Series Classification

Shuguo Hu, Jun Hu, Junwei Lv, Huaiwen Zhang

Abstract: Early Time Series Classification (ETSC) aims to predict class labels using only prefixes (partial sequences) of time series, which is crucial for applications requiring prompt decision-making. However, time series prefixes, with their limited data length, pose significant challenges for models to recognize patterns and provide reliable predictions based on incomplete data. Enhancing ETSC by addressing this limitation is essential. Existing ETSC methods primarily focus on improving feature extractors or refining stopping strategies, yet they often fail to overcome the core issue of data insufficiency in early segments. We present EarlyMix, which employs a hierarchical mixing strategy comprising Sample Mixing and Latent Mixing to augment data and enhance feature representation. This method significantly improves model performance by enabling the extraction of more informative and robust features from time series prefixes. Extensive experiments on widely-used benchmark datasets demonstrate the superior performance of EarlyMix over baselines.

External IDs:dblp:conf/icmcs/HuHLZ25