TSEM: Temporally Weighted Spatiotemporal Explainable Neural Network for Multivariate Time Series

TL;DR

This paper introduces TSEM, a novel neural network that combines RNN and CNN with attention mechanisms to improve interpretability and accuracy in multivariate time series analysis.

Contribution

The paper proposes TSEM, merging CAM and attention in a unified model for better interpretability and performance on multivariate time series data.

Findings

TSEM outperforms XCM in accuracy.

TSEM satisfies interpretability criteria like causality and fidelity.

TSEM is comparable to STAM in accuracy.

Abstract

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.