Confidence-Guided Learning Process for Continuous Classification of Time Series

Abstract

In the real world, the class of a time series is usually labeled at the final time, but many applications require to classify time series at every time point. e.g. the outcome of a critical patient is only determined at the end, but he should be diagnosed at all times for timely treatment. Thus, we propose a new concept: Continuous Classification of Time Series (CCTS). It requires the model to learn data in different time stages. But the time series evolves dynamically, leading to different data distributions. When a model learns multi-distribution, it always forgets or overfits. We suggest that meaningful learning scheduling is potential due to an interesting observation: Measured by confidence, the process of model learning multiple distributions is similar to the process of human learning multiple knowledge. Thus, we propose a novel Confidence-guided method for CCTS (C3TS). It can imitate the alternating human confidence described by the Dunning-Kruger Effect. We define the objective- confidence to arrange data, and the self-confidence to control the learning duration. Experiments on four real-world datasets show that C3TS is more accurate than all baselines for CCTS.

arXiv comment20 pages, 12 figures

References in corpus (12)

• Overcoming catastrophic forgetting in neural networks
• Deep learning for time series classification: a review
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• A continual learning survey: Defying forgetting in classification tasks
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• Experience Replay for Continual Learning
• Predictive Uncertainty Estimation via Prior Networks
• Approaches and Applications of Early Classification of Time Series: A Review
• Addressing Failure Prediction by Learning Model Confidence
• An Empirical Exploration of Curriculum Learning for Neural Machine Translation
• Quantifying Uncertainties in Natural Language Processing Tasks