Encoding time-series explanations through self-supervised model behavior consistency

O Queen, T Hartvigsen, T Koker, H He… - Advances in …, 2024 - proceedings.neurips.cc
Interpreting time series models is uniquely challenging because it requires identifying both
the location of time series signals that drive model predictions and their matching to an …

Time-series Shapelets with Learnable Lengths

A Yamaguchi, K Ueno, H Kashima - Proceedings of the 32nd ACM …, 2023 - dl.acm.org
Shapelets are subsequences that are effective for classifying time-series instances.
Learning shapelets by a continuous optimization has recently been studied to improve …

Toward Learning Model-Agnostic Explanations for Deep Learning-Based Signal Modulation Classifiers

Y Tian, D Xu, E Tong, R Sun, K Chen… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Recent advances in deep learning (DL) have brought tremendous gains in signal
modulation classification. However, DL-based classifiers lack transparency and …

Learning Counterfactual Explanations with Intervals for Time-series Classification

A Yamaguchi, K Ueno, R Shingaki… - Proceedings of the 33rd …, 2024 - dl.acm.org
The need for explainability in time-series classification models has been increasing.
Counterfactual explanations recommend how to modify the features of an original instance …

A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecasting

PD Arsenault, S Wang, JM Patenande - arXiv preprint arXiv:2407.15909, 2024 - arxiv.org
Artificial Intelligence (AI) models have reached a very significant level of accuracy. While
their superior performance offers considerable benefits, their inherent complexity often …

Explaining deep multi-class time series classifiers

R Doddaiah, PS Parvatharaju, E Rundensteiner… - … and Information Systems, 2024 - Springer
Explainability helps users trust deep learning solutions for time series classification.
However, existing explainability methods for multi-class time series classifiers focus on one …