Special Issue on Interpretability
We are co-editing a Special Issue on Explainable and Interpretable Machine Learning and Data Mining in the Data Mining and Knowledge Discovery journal.
Explainable and Interpretable Machine Learning (XI-ML) aims at bringing together research from interpretable and explainable machine learning, also relating to data mining and knowledge discovery. This special issue will provide a leading forum for timely, in-depth presentation of recent advances in explainable and interpretable machine learning and data mining. We aim to tackle these themes from the modeling and learning perspective, targeting interpretable methods and models being able to explain themselves and their output, respectively. Thus, this call covers a wide range of potential topics.
Deadline for submissions is March 31st, 2021. Do submit!
Best Paper Award @DKE 2016
“An analysis of ontologies and their success factors for application to business”
by Christina Sachsenhofer-Feilmayr and Wolfram Wöß
has been selected as the best 2016 Data and Knowledge Engineering (DKE) journal paper by the evaluation committee headed by Dr. Jarke:
Dr. Valeria de Antonellis
Dr. Matthias Jarke (chairperson)
Dr. Antoni Olive
Dr. Panos Vassiliadis.
The public announcement of the Best DKE paper is planned to take place at the ER 2020 conference.
"Many thanks to Lisa Ehrlinger. One of her first tasks in my team was to help us revising the paper. In addition to the textual work, Lisa also contributed to improving the content." (Wolfram Wöß)
Alm-Talk zum Thema "Digitalisierung und Freiwilliges Engagement" unter Mitwirkung der JKU Informatik (a.Univ.-Prof. Birgit Pröll, FAW).
Digitale Transformation ist im 21. Jahrhundert auch für den Freiwilligensektor zu einem „Game Changer“ geworden. Wie aber kann Wertschätzung für freiwilliges Engagement in geeigneter Art und Weise digitalisiert werden, um damit den unentgeltlichen Dienst an der Gesellschaft weiter aufzuwerten?
Über diese spannende Frage diskutierten am 26.8. am Alm-Talk-Podium unter Moderation von Niki Dürk (X-Net) die interdisziplinär zusammengesetzte Runde: Anton Hörting, Christoph Angster (beide Sozialministerium), Birgit Pröll (JKU), Marianne Pührerfellner (Kunstuni Linz), Sandra Horvatits (oöRK), Wolfgang Kronsteiner (oöLFV) und Gerald Heerdegen (Fahnen-Gärtner).
Im Zuge des Alm-Talks wurden der digitale Freiwilligenpass des Sozialministeriums sowie das FFG-COIN geförderte Forschungsprojekt "iVolunteer" vorgestellt - Partner*innen: JKU (Konsortialführung FAW, TK/CIS, Inst. für Organisation), Kunstuni Linz, FH-OÖ Hagenberg, x-Net, blp, GTN, Solarys, oöRK, oöLFV, Eu. Forum Alpbach.
Foto: Philipp Huber
Paper on Interpretability Published
The paper "On cognitive preferences and the plausibility of rule-based models" has finally been published. In it, we discuss various aspects of interpretability, propose to distinguish between syntatic, epistemic, and pragmatic interpretability, and argue that complexity measures such as the size of a decision tree or a rule set only address the first of these dimensions. We also report on a set of crowd-sourcing experiments that support this view, and discuss results on human cognitive biases with respect to the interpretability of rule-based theories.
Best Paper Award @DBKDA 2018
Lisa Ehrlinger, Bernhard Werth, and Wolfram Wöß received a Best Paper Award for the publication “QuaIIe: A Data Quality Assessment Tool for Integrated Information Systems”, which was presented during DBKDA 2018, the Tenth International Conference on Advances in Databases, Knowledge, and Data Applications, held in Nice, France during May 20-24, 2018. The selection was based on the review of the original submission, the camera-ready version, and the presentation during the conference.
FAW @ Lange Nacht der Forschung 2018
The Institute for Application Oriented Knowledge Processing (FAW) at the Johannes Kepler University Linz (JKU) also participates in Lange Nacht der Forschung 2018 (LNF18) at Softwarepark Hagenberg.
Interested in our presentations?
Our researchers will gladly give you an insight into some of our research projects and look forward to interesting discussions.