TSEM: Temporally Weighted Spatiotemporal Explainable Neural Network for Multivariate Time Series
This work addresses the need for trustworthy and interpretable AI in time series analysis, though it appears incremental as it combines existing strategies.
The paper tackled the problem of improving interpretability in deep learning models for multivariate time series by merging Class Activation Mapping and Attention Mechanism into a single system called TSEM, resulting in outperforming XCM and matching STAM in accuracy while meeting interpretability criteria.
Deep learning has become a one-size-fits-all solution for technical and business domains thanks to its flexibility and adaptability. It is implemented using opaque models, which unfortunately undermines the outcome trustworthiness. In order to have a better understanding of the behavior of a system, particularly one driven by time series, a look inside a deep learning model so-called posthoc eXplainable Artificial Intelligence (XAI) approaches, is important. There are two major types of XAI for time series data, namely model-agnostic and model-specific. Model-specific approach is considered in this work. While other approaches employ either Class Activation Mapping (CAM) or Attention Mechanism, we merge the two strategies into a single system, simply called the Temporally Weighted Spatiotemporal Explainable Neural Network for Multivariate Time Series (TSEM). TSEM combines the capabilities of RNN and CNN models in such a way that RNN hidden units are employed as attention weights for the CNN feature maps temporal axis. The result shows that TSEM outperforms XCM. It is similar to STAM in terms of accuracy, while also satisfying a number of interpretability criteria, including causality, fidelity, and spatiotemporality.