Vol-3761
urn:nbn:de:0074-3761-3

Copyright © 2024 for the individual papers by the papers' authors. Copyright © 2024 for the volume as a collection by its editors. This volume and its papers are published under the Creative Commons License Attribution 4.0 International (CC BY 4.0).

TempXAI 2024
Explainable AI for Time Series and Data Streams 2024

Proceedings of the Workshop on Explainable AI for Time Series and Data Streams (TempXAI 2024)
co-located with The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2024)

Vilnius, Lithuania, September 9th, 2024.

Edited by

Zahraa Abdallah *
Fabian Fumagalli
Barbara Hammer
Eyke Hüllermeier *
Matthias Jakobs
Emmanuel Müller *
Maximilian Muschalik *
Panagiotis Papapetrou
Amal Saadallah
George Tzagkarakis *

* University of Bristol, UK
** Bielefeld University, Germany
*** LMU Munich, Germany
**** Lamarr Institute for Machine Learning and Artificial Intelligence, Germany
***** Research Center Trustworthy Data Science and Security, Germany
****** Stockholm University, Sweden
******* FORTH-ICS, Greece

Table of Contents

Preface
Summary: There were 5 submissions for peer-review, out of which we accepted 4 papers were accepted for this volume. In addition, we publish two extended abstracts of the tutorial that we give as a part of the workshop program.

Extended Abstracts

Explaining Change in Models and Data with Global Feature Importance and Effects 1-6
Maximilian Muschalik, Fabian Fumagalli, Barbara Hammer, Eyke Hüllermeier
Online Explainable Forecasting using Regions of Competence 7-11
Amal Saadallah, Matthias Jakobs

Research Papers

Finding the DeepDream for Time Series: Activation Maximization for Univariate Time Series 12-27
Udo Schlegel, Daniel A. Keim, Tobias Sutter
Optimal Robust Simplifications for Explaining Time Series Classifications 28-43
Jan Arne Telle, Cèsar Ferri, Brigt Håvardstun
Interpreting Outliers in Time Series Data through Decoding Autoencoder 44-57
Patrick Knab, Sascha Marton, Christian Bartelt, Robert Fuder
Explainable Federated Learning by Incremental Decision Trees 58-69
Parisa Jamshidi, Sławomir Nowaczyk, Mahmoud Rahat, Zahra Taghiyarrenani

2024-09-17: submitted by Amal Saadallah, metadata incl. bibliographic data published under Creative Commons CC0
2024-09-17: published on CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) |valid HTML5|