Improving Time Series Classification with Representation Soft Label Smoothing
This work addresses overfitting in time series classification, an incremental improvement for researchers and practitioners in this domain.
The paper tackled overfitting in deep neural networks for time series classification by proposing representation soft label smoothing, a method that generates more reliable soft labels, and showed it yields competitive results compared to baseline hard labels across models with varying structures.
Previous research has indicated that deep neural network based models for time series classification (TSC) tasks are prone to overfitting. This issue can be mitigated by employing strategies that prevent the model from becoming overly confident in its predictions, such as label smoothing and confidence penalty. Building upon the concept of label smoothing, we propose a novel approach to generate more reliable soft labels, which we refer to as representation soft label smoothing. We apply label smoothing, confidence penalty, and our method representation soft label smoothing to several TSC models and compare their performance with baseline method which only uses hard labels for training. Our results demonstrate that the use of these enhancement techniques yields competitive results compared to the baseline method. Importantly, our method demonstrates strong performance across models with varying structures and complexities.