---
title: "Two Birds with One Stone: Series Saliency for Accurate and Interpretable Multivariate Time Series Forecasting"
authors:
  - "Qingyi Pan"
  - "Wenbo Hu"
  - "Ning Chen"
doi: "10.24963/ijcai.2021/397"
url: "https://ijcai.org/proceedings/2021/397"
pdf: "https://ijcai.org/proceedings/2021/0397.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "2884-2891"
track: "Main Track"
keywords:
  - "Machine Learning: Explainable/Interpretable Machine Learning"
  - "Machine Learning: Time-series; Data Streams"
---

# Two Birds with One Stone: Series Saliency for Accurate and Interpretable Multivariate Time Series Forecasting

Qingyi Pan, Wenbo Hu, Ning Chen

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 2884-2891. DOI: [10.24963/ijcai.2021/397](https://doi.org/10.24963/ijcai.2021/397)

## Abstract

It is important yet challenging to perform accurate and interpretable time series forecasting. Though deep learning methods can boost forecasting accuracy, they often sacrifice interpretability. In this paper, we present a new scheme of series saliency to boost both accuracy and interpretability. By extracting series images from sliding windows of the time series, we design series saliency as a mixup strategy with a learnable mask between the series images and their perturbed versions. Series saliency is model agnostic and performs as an adaptive data augmentation method for training deep models. Moreover, by slightly changing the objective, we optimize series saliency to find a mask for interpretable forecasting in both feature and time dimensions. Experimental results on several real datasets demonstrate that series saliency is effective to produce accurate time-series forecasting results as well as generate temporal interpretations.