Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Damke, Clemens"'
Autor:
Damke, Clemens, Hüllermeier, Eyke
In this work, we study the influence of domain-specific characteristics when defining a meaningful notion of predictive uncertainty on graph data. Previously, the so-called Graph Posterior Network (GPN) model has been proposed to quantify uncertainty
Externí odkaz:
http://arxiv.org/abs/2409.04159
Autor:
Damke, Clemens, Hüllermeier, Eyke
We address the problem of uncertainty quantification for graph-structured data, or, more specifically, the problem to quantify the predictive uncertainty in (semi-supervised) node classification. Key questions in this regard concern the distinction b
Externí odkaz:
http://arxiv.org/abs/2406.04041
The Go programming language offers strong protection from memory corruption. As an escape hatch of these protections, it provides the unsafe package. Previous studies identified that this unsafe package is frequently used in real-world code for sever
Externí odkaz:
http://arxiv.org/abs/2306.00694
Autor:
Damke, Clemens, Hüllermeier, Eyke
Publikováno v:
24th International Conference on Discovery Science (2021) 166-180
Graph neural networks (GNNs) have been successfully applied in many structured data domains, with applications ranging from molecular property prediction to the analysis of social networks. Motivated by the broad applicability of GNNs, we propose the
Externí odkaz:
http://arxiv.org/abs/2104.08869
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 ba
Externí odkaz:
http://arxiv.org/abs/2007.00346