TY - CHAP A1 - Strickert, Marc A1 - Keilwagen, Jens A1 - Schleif, Frank-Michael A1 - Villmann, Thomas A1 - Biehl, Michael ED - Cabestany, Joan ED - Sandoval Hernández, Francisco ED - Prieto, Alberto ED - Corchado, Juan M. T1 - Matrix Metric Adaptation for Improved Linear Discriminant Analysis of Biomedical Data T2 - Bio-Inspired Systems: Computational and Ambient Intelligence, 10th International Work-Conference on Artificial Neural Networks, IWANN 2009, Salamanca, Spain, June 10-12, 2009. Proceedings, Part I Y1 - 2009 U6 - https://doi.org/10.1007/978-3-642-02478-8_117 SP - 933 EP - 940 ER - TY - JOUR A1 - Strickert, Marc A1 - Schleif, Frank-Michael A1 - Villmann, Thomas A1 - Seiffert, Udo ED - Biehl, Michael ED - Hammer, Barbara ED - Verleysen, Michel ED - Villmann, Thomas T1 - Unleashing Pearson Correlation for Faithful Analysis of Biomedical Data JF - Similarity-Based Clustering, Recent Developments and Biomedical Applications [outcome of a Dagstuhl Seminar] Y1 - 2009 U6 - https://doi.org/10.1007/978-3-642-01805-3_5 SP - 70 EP - 91 ER - TY - CHAP A1 - Simmuteit, Stephan A1 - Schleif, Frank-Michael A1 - Villmann, Thomas A1 - Kostrzewa, Markus ED - Carlos Prı́ncipe, José ED - Miikkulainen, Risto T1 - Hierarchical PCA Using Tree-SOM for the Identification of Bacteria T2 - Advances in Self-Organizing Maps, 7th International Workshop, WSOM 2009, St. Augustine, FL, USA, June 8-10, 2009. Proceedings Y1 - 2009 U6 - https://doi.org/10.1007/978-3-642-02397-2_31 SP - 272 EP - 280 ER - TY - CHAP A1 - Villmann, Thomas A1 - Schleif, Frank-Michael T1 - Functional vector quantization by neural maps T2 - First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2009, Grenoble, France, August 26-28, 2009 Y1 - 2009 U6 - https://doi.org/10.1109/WHISPERS.2009.5289064 SP - 1 EP - 4 ER - TY - JOUR A1 - Schleif, Frank-Michael A1 - Villmann, Thomas A1 - Ongyerth, Matthias T1 - Supervised data analysis and reliability estimation with exemplary application for spectral data JF - Neurocomputing Y1 - 2009 U6 - https://doi.org/10.1016/j.neucom.2008.12.040 VL - 72 IS - 16-18 SP - 3590 EP - 3601 ER - TY - CHAP A1 - Schleif, Frank-Michael A1 - Villmann, Thomas T1 - Neural Maps and Learning Vector Quantization - Theory and Applications T2 - 17th European Symposium on Artificial Neural Networks, ESANN 2009, Bruges, Belgium, April 22-24, 2009, Proceedings Y1 - 2009 ER - TY - CHAP A1 - Köping, Lukas A1 - Mühsam, Thomas A1 - Ofenberg, Christian A1 - Czech, Bernhard A1 - Bernard, Michael A1 - Schmer, Jens A1 - Deinzer, Frank T1 - Indoor Naviagtion Using Step and Turn Detection Together With Floor Map Information T2 - Proceedings of the 1st International Workshop on Uncertainty in Ambient Intelligence Y1 - 2013 ER - TY - JOUR A1 - Weber, Kristin T1 - Data Governance BT - Organisation des Stammdatenmanagements JF - IT-Governance Y1 - 2012 UR - http://permalink.bibkatalog.de/BV042408357 VL - 6 IS - 13 SP - 3 EP - 8 ER - TY - JOUR A1 - Ebert, Nico A1 - Weber, Kristin T1 - Sicherheit von Cloud-basierten Plattformen zur Anwendungsintegration BT - eine Bewertung aktueller Angebote JF - FHWS Science Journal N2 - Cloud-basierte Plattformen zur Anwendungsintegration versprechen die einfache und kostengünstige Integration zwischen Anwendungen in der Cloud und bestehenden „On-Premise“- Anwendungen. Sie bieten zahlreiche Anwendungsadapter und erlauben den grafischen Entwurf, die Ausführung und die Verwaltung von komplexen Integrationsprozessen in der Cloud. Allerdings sind sie sicherheitskritische Elemente innerhalb der IT-Architektur, da sie Zugriff auf unterschiedliche Anwendungen und Daten des Unternehmens haben können. Daher stellt sich die Frage, inwiefern notwendige Sicherheitsanforderungen durch die Anbieter Cloud-basierter Plattformen erfüllt werden. In diesem Artikel werden sieben ausgewählte Integrationsplattformen detaillierter betrachtet und anhand der Sicherheitsanforderungen des Bundesamtes für Sicherheit in der Informationstechnik (BSI) bewertet. KW - Cloud-basierte Integrationsplattform KW - Integration-platrom-as-a-service KW - Sicherheitsanforderung KW - Informationssicherheit KW - Datenschutz Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:863-opus-2975 VL - 3(2015) IS - 2 SP - 10 EP - 22 ER - TY - JOUR A1 - Väth, Philipp A1 - Frühwald, Alexander M. A1 - Paaßen, Benjamin A1 - Gregorová, Magda T1 - Diffusion-based Visual Counterfactual Explanations - Towards Systematic Quantitative Evaluation JF - CoRR N2 - Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality. However, it is currently difficult to compare the performance of these VCE methods as the evaluation procedures largely vary and often boil down to visual inspection of individual examples and small scale user studies. In this work, we propose a framework for systematic, quantitative evaluation of the VCE methods and a minimal set of metrics to be used. We use this framework to explore the effects of certain crucial design choices in the latest diffusion-based generative models for VCEs of natural image classification (ImageNet). We conduct a battery of ablation-like experiments, generating thousands of VCEs for a suite of classifiers of various complexity, accuracy and robustness. Our findings suggest multiple directions for future advancements and improvements of VCE methods. By sharing our methodology and our approach to tackle the computational challenges of such a study on a limited hardware setup (including the complete code base), we offer a valuable guidance for researchers in the field fostering consistency and transparency in the assessment of counterfactual explanations. Y1 - 2023 U6 - https://doi.org/10.48550/arXiv.2308.06100 VL - abs/2308.06100 ER - TY - JOUR A1 - Boget, Yoann A1 - Gregorová, Magda A1 - Kalousis, Alexandros T1 - GrannGAN: Graph annotation generative adversarial networks JF - CoRR N2 - We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features. We follow the strategy of implicit distribution modelling via generative adversarial network (GAN) combined with permutation equivariant message passing architecture operating over the sets of nodes and edges. This enables generating the feature vectors of all the graph objects in one go (in 2 phases) as opposed to a much slower one-by-one generations of sequential models, prevents the need for expensive graph matching procedures usually needed for likelihood-based generative models, and uses efficiently the network capacity by being insensitive to the particular node ordering in the graph representation. To the best of our knowledge, this is the first method that models the feature distribution along the graph skeleton allowing for generations of annotated graphs with user specified structures. Our experiments demonstrate the ability of our model to learn complex structured distributions through quantitative evaluation over three annotated graph datasets. Y1 - 2022 U6 - https://doi.org/10.48550/arXiv.2212.00449 VL - abs/2212.00449 ER - TY - JOUR A1 - Boget, Yoann A1 - Gregorová, Magda A1 - Kalousis, Alexandros T1 - Vector-Quantized Graph Auto-Encoder JF - CoRR N2 - In this work, we addresses the problem of modeling distributions of graphs. We introduce the Vector-Quantized Graph Auto-Encoder (VQ-GAE), a permutation-equivariant discrete auto-encoder and designed to model the distribution of graphs. By exploiting the permutation-equivariance of graph neural networks (GNNs), our autoencoder circumvents the problem of the ordering of the graph representation. We leverage the capability of GNNs to capture local structures of graphs while employing vector-quantization to prevent the mapping of discrete objects to a continuous latent space. Furthermore, the use of autoregressive models enables us to capture the global structure of graphs via the latent representation. We evaluate our model on standard datasets used for graph generation and observe that it achieves excellent performance on some of the most salient evaluation metrics compared to the state-of-the-art. Y1 - 2023 U6 - https://doi.org/10.48550/arXiv.2306.07735 VL - abs/2306.07735 ER - TY - CHAP A1 - Boget, Yoann A1 - Gregorová, Magda A1 - Kalousis, Alexandros T1 - Permutation Equivariant Generative Adversarial Networks for Graphs T2 - Neural Compression Workshop (CoRR) N2 - One of the most discussed issues in graph generative modeling is the ordering of the representation. One solution consists of using equivariant generative functions, which ensure the ordering invariance. After having discussed some properties of such functions, we propose 3G-GAN, a 3-stages model relying on GANs and equivariant functions. The model is still under development. However, we present some encouraging exploratory experiments and discuss the issues still to be addressed. Y1 - 2021 U6 - https://doi.org/10.48550/arXiv.2112.03621 VL - abs/2112.03621 ER - TY - CHAP A1 - Boget, Yoann A1 - Gregorová, Magda A1 - Kalousis, Alexandros ED - Balasubramanian, Vineeth N. ED - Tsang, Ivor W. T1 - Graph annotation generative adversarial networks T2 - Asian Conference on Machine Learning, ACML 2022, 12-14 December 2022, Hyderabad, India N2 - We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features. We follow the strategy of implicit distribution modelling via generative adversarial network (GAN) combined with permutation equivariant message passing architecture operating over the sets of nodes and edges. This enables generating the feature vectors of all the graph objects in one go (in 2 phases) as opposed to a much slower one-by-one generations of sequential models, prevents the need for expensive graph matching procedures usually needed for likelihood-based generative models, and uses efficiently the network capacity by being insensitive to the particular node ordering in the graph representation. To the best of our knowledge, this is the first method that models the feature distribution along the graph skeleton allowing for generations of annotated graphs with user specified structures. Our experiments demonstrate the ability of our model to learn complex structured distributions through quantitative evaluation over three annotated graph datasets. Y1 - 2022 U6 - https://doi.org/10.48550/arXiv.2212.00449 VL - 189 SP - 16 EP - 16 ER -