# Focusing on What is Relevant: Time-Series Learning and Understanding using Attention

arXiv: https://arxiv.org/abs/1806.08523 · HTML: https://mlsanity.com/paper/1806.08523/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2018.

## Built on by (most cited first, 8 of 8)

- [Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey](https://mlsanity.com/paper/2104.00950/) (2021)
- [Interpretation of Time-Series Deep Models: A Survey](https://mlsanity.com/paper/2305.14582/) (2023)
- [Time is Not Enough: Time-Frequency based Explanation for Time-Series Black-Box Models](https://mlsanity.com/paper/2408.03636/) (2024)
- [ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques](https://mlsanity.com/paper/2209.03798/) (2022)
- [Prototypes as Explanation for Time Series Anomaly Detection](https://mlsanity.com/paper/2307.01601/) (2023)
- [ECATS: Explainable-by-design concept-based anomaly detection for time series](https://mlsanity.com/paper/2405.10608/) (2024)
- [SSET: Swapping-Sliding Explanation for Time Series Classifiers in Affect Detection](https://mlsanity.com/paper/2410.12996/) (2024)
- [Guided by Stars: Interpretable Concept Learning Over Time Series via Temporal Logic Semantics](https://mlsanity.com/paper/2511.04244/) (2025)

## Abstract (arXiv)

This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various tasks, including data completion, key-frame detection and classification. The method uses the whole input sequence to calculate an attention value for each time step. This results in more focused attention values and more plausible visualisation than previous methods. We apply the proposed method to three different tasks. Experimental results show that the proposed network produces comparable results to a state of the art. In addition, the network provides better interpretability of the decision, that is, it generates more significant attention weight to related frames compared to similar techniques attempted in the past.