TY - CONF AB - Current GNN architectures use a vertex neighborhood aggregation scheme, which limits their discriminative power to that of the 1-dimensional Weisfeiler-Lehman (WL) graph isomorphism test. Here, we propose a novel graph convolution operator that is based on the 2-dimensional WL test. We formally show that the resulting 2-WL-GNN architecture is more discriminative than existing GNN approaches. This theoretical result is complemented by experimental studies using synthetic and real data. On multiple common graph classification benchmarks, we demonstrate that the proposed model is competitive with state-of-the-art graph kernels and GNNs. AU - Damke, Clemens AU - Melnikov, Vitaly AU - Hüllermeier, Eyke ED - Jialin Pan, Sinno ED - Sugiyama, Masashi ID - 19953 KW - graph neural networks KW - Weisfeiler-Lehman test KW - cycle detection T2 - Proceedings of the 12th Asian Conference on Machine Learning (ACML 2020) TI - A Novel Higher-order Weisfeiler-Lehman Graph Convolution VL - 129 ER - TY - CONF AU - Spliethöver, Maximilian AU - Wachsmuth, Henning ID - 20139 T2 - Proceedings of the 7th Workshop on Argument Mining (ArgMining 2020) TI - Argument from Old Man's View: Assessing Social Bias in Argumentation ER - TY - JOUR AU - Otroshi, Mortaza AU - Meschut, Gerson ID - 20170 IS - 7/20 JF - Umformtechnik Blech Rohre Profile SN - 0300-3167 TI - Spannungszustandsabhängige Schädigungsmodellierung zum Halbhohlstanznieten ER - TY - GEN AU - Hemsen, Paul AU - Hesse, Marc AU - Löken, Nils AU - Nouri, Zahra ID - 20191 T2 - 2nd Crowdworking Symposium TI - Platform-independent Reputation and Qualification System for Crowdwork ER - TY - GEN AB - In many real-world applications, the relative depth of objects in an image is crucial for scene understanding, e.g., to calculate occlusions in augmented reality scenes. Predicting depth in monocular images has recently been tackled using machine learning methods, mainly by treating the problem as a regression task. Yet, being interested in an order relation in the first place, ranking methods suggest themselves as a natural alternative to regression, and indeed, ranking approaches leveraging pairwise comparisons as training information ("object A is closer to the camera than B") have shown promising performance on this problem. In this paper, we elaborate on the use of so-called \emph{listwise} ranking as a generalization of the pairwise approach. Listwise ranking goes beyond pairwise comparisons between objects and considers rankings of arbitrary length as training information. Our approach is based on the Plackett-Luce model, a probability distribution on rankings, which we combine with a state-of-the-art neural network architecture and a sampling strategy to reduce training complexity. An empirical evaluation on benchmark data in a "zero-shot" setting demonstrates the effectiveness of our proposal compared to existing ranking and regression methods. AU - Lienen, Julian AU - Hüllermeier, Eyke ID - 20211 T2 - arXiv:2010.13118 TI - Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce model ER - TY - JOUR AB - The challenge of designing new tunable nonlinear dielectric materials with tailored properties has attracted an increasing amount of interest recently. Herein, we study the effective nonlinear dielectric response of a stochastic paraelectric-dielectric composite consisting of equilibrium distributions of circular and partially penetrable disks (or parallel, infinitely long, identical, partially penetrable, circular cylinders) of a dielectric phase randomly dispersed in a continuous matrix of a paraelectric phase. The random microstructures were generated using the Metropolis Monte Carlo algorithm. The evaluation of the effective permittivity and tunability were carried out by employing either a Landau thermodynamic model or its Johnson’s approximation to describe the field-dependent permittivity of the paraelectric phase and solving continuum-electrostatics equations using finite element calculations. We reveal that the percolation threshold in this composite governs the critical behavior of the effective permittivity and tunability. For microstructures below the percolation threshold, our simulations demonstrate a strong nonlinear behaviour of the field-dependent effective permittivity and very high tunability that increases as a function of dielectric phase concentration. Above the percolation threshold, the effective permittivity shows the tendency to linearization and the tunability dramatically drops down. The highly reduced permittivity and extraordinarily high tunability are obtained for the composites with dielectric impenetrable disks at high concentrations, in which the triggering of the percolation transition is avoided. The reported results cast light on distinct nonlinear behaviour of 2D and 3D stochastic composites and can guide the design of novel composites with the controlled morphology and tailored permittivity and tunability. AU - Myroshnychenko, Viktor AU - Smirnov, Stanislav AU - Jose, Pious Mathews Mulavarickal AU - Brosseau, Christian AU - Förstner, Jens ID - 20233 JF - Acta Materialia SN - 1359-6454 TI - Nonlinear dielectric properties of random paraelectric-dielectric composites VL - 203 ER - TY - THES AU - Homt, Martina ID - 28416 TI - Die Anbahnung einer forschenden Grundhaltung im Praxissemester – eine empirische Analyse von Bedingungen und Entwicklungsverläufen ER - TY - JOUR AU - Engels, Gregor ID - 29045 JF - Gruppe. Interaktion. Organisation. Zeitschrift für Angewandte Organisationspsychologie (GIO) SN - 2366-6145 TI - Der digitale Fußabdruck, Schatten oder Zwilling von Maschinen und Menschen ER - TY - GEN AB - Previous accounting research shows that taxes affect decision making by individuals and firms. Most studies assume that agents have an accurate perception regarding their tax burden. However, there is a growing body of literature analyzing whether taxes are indeed perceived correctly. We review 127 studies on the measurement of tax misperception and its behavioral implications. The review reveals that many taxpayers have substantial tax misperceptions that lead to biased decision making. We develop a Behavioral Taxpayer Response Model on the impact of provided tax information on tax perception. Besides individual traits, characteristics of the tax information and the decision environment determine the extent of tax misperception. We discuss opportunities for future research and methodological limitations. While there is much evidence on tax misperception at the individual level, we hardly find any research at the firm level. Little is known about the real effects of managers’ tax misperception and on how tax information is strategically managed to impact stakeholders. This research gap is surprising as a large part of the accounting literature analyzes decision making and disclosure of firms. We recommend a mixed-method approach combining experiments, surveys, and archival data analyses to improve the knowledge on tax misperception and its consequences. AU - Blaufus, Kay AU - Chirvi, Malte AU - Huber, Hans-Peter AU - Maiterth, Ralf AU - Sureth-Sloane, Caren ID - 21406 TI - Tax Misperception and Its Effects on Decision Making - a Literature Review VL - No. 39 ER - TY - GEN AU - Bornemann, Tobias AU - Schipp, Adrian AU - Sureth-Sloane, Caren ID - 21407 TI - 2018/2019 Umfrage zur Steuerkomplexität in deutschen Finanzverwaltungen ER -