DIVERSIFY to Generalize: Learning Generalized Representations for Time Series Classification
Time series classification is an important problem in real world. Due to its nonstationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen distributions. In this paper, we propose to view the time series classification problem from the distribution perspective. We argue that the temporal complexity attributes to the unknown latent distributions within. To this end, we propose DIVERSIFY to learn generalized representations for time series classification. DIVERSIFY takes an iterative process: it first obtains the worst-case distribution scenario via adversarial training, then matches the distributions between all segments. We also present some theoretical insights. Extensive experiments on gesture recognition, speech commands recognition, and sensor-based human activity recognition demonstrate that DIVERSIFY significantly outperforms other baselines while effectively characterizing the latent distributions by qualitative and quantitative analysis.
PDF Abstract
Speech Commands
