Logo des Repositoriums

Auflistung nach Autor:in "Finzel, Bettina"

1 - 5 von 5
  • Zeitschriftenartikel
    Generating Explanations for Conceptual Validation of Graph Neural Networks: An Investigation of Symbolic Predicates Learned on Relevance-Ranked Sub-Graphs
    (KI - Künstliche Intelligenz: Vol. 36, No. 0, 2022) Finzel, Bettina; Saranti, Anna; Angerschmid, Alessa; Tafler, David; Pfeifer, Bastian; Holzinger, Andreas
    Graph Neural Networks (GNN) show good performance in relational data classification. However, their contribution to concept learning and the validation of their output from an application domain’s and user’s perspective have not been thoroughly studied. We argue that combining symbolic learning methods, such as Inductive Logic Programming (ILP), with statistical machine learning methods, especially GNNs, is an essential forward-looking step to perform powerful and validatable relational concept learning. In this contribution, we introduce a benchmark for the conceptual validation of GNN classification outputs. It consists of the symbolic representations of symmetric and non-symmetric figures that are taken from a well-known Kandinsky Pattern data set. We further provide a novel validation framework that can be used to generate comprehensible explanations with ILP on top of the relevance output of GNN explainers and human-expected relevance for concepts learned by GNNs. Our experiments conducted on our benchmark data set demonstrate that it is possible to extract symbolic concepts from the most relevant explanations that are representative of what a GNN has learned. Our findings open up a variety of avenues for future research on validatable explanations for GNNs.
  • Zeitschriftenartikel
    Jedes Jahr: Informelle Kontakte knüpfen und sich sowohl fachlich als auch beruflich inspirieren lassen
    (Vol. 40, 30 Jahre Fachgruppe Frauen und Informatik, 2016) Finzel, Bettina
  • Zeitschriftenartikel
  • Zeitschriftenartikel
    Mutual Explanations for Cooperative Decision Making in Medicine
    (KI - Künstliche Intelligenz: Vol. 34, No. 2, 2020) Schmid, Ute; Finzel, Bettina
    Exploiting mutual explanations for interactive learning is presented as part of an interdisciplinary research project on transparent machine learning for medical decision support. Focus of the project is to combine deep learning black box approaches with interpretable machine learning for classification of different types of medical images to combine the predictive accuracy of deep learning and the transparency and comprehensibility of interpretable models. Specifically, we present an extension of the Inductive Logic Programming system Aleph to allow for interactive learning. Medical experts can ask for verbal explanations. They can correct classification decisions and in addition can also correct the explanations. Thereby, expert knowledge can be taken into account in form of constraints for model adaption.
  • Konferenzbeitrag
    Towards Understanding Mobility in Museums
    (Datenbanksysteme für Business, Technologie und Web (BTW 2017) - Workshopband, 2017) Elmamooz, Golnaz; Finzel, Bettina; Nicklas, Daniela
    Data mining techniques can provide valuable insight to understand mobility in museums. However, the results of such techniques might not be easily understood by the museum staff. In this paper, we propose a graph-based approach to model museum exhibitions, sensor locations, and guiding tasks. We further discuss how route-based trajectory mining can be adapted to work with this graph model and which challenges need to be addressed to cope with the graph dynamics and the continuous flow of sensor data. Based on the demands of two target groups, curators and visitors, three applications are proposed: a museum graph editor, a mobile museum guide, and a curator decision support. We propose an architecture for a platform that provides context information and data mining results to such applications. We claim that our proposed platform can cover many aspects and demands that arise in the museum environment today.