20 citations · 158 across the 42 of their papers we have counts for
5 papers · 1 filter
Discovering Locally Maximal Bipartite Subgraphs
Dominik Dürrschnabel, Tom Hanika, Gerd Stumme
Induced bipartite subgraphs of maximal vertex cardinality are an essential concept for the analysis of graphs. Yet, discovering them in large graphs is known to be computationally…
Intrinsic Dimension for Large-Scale Geometric Learning
Maximilian Stubbemann, Tom Hanika, Friedrich Martin Schneider
The concept of dimension is essential to grasp the complexity of data. A naive approach to determine the dimension of a dataset is based on the number of attributes. More sophistic…
Conceptual Views of Neural Networks: A Framework for Neuro-Symbolic Analysis
Johannes Hirth, Tom Hanika
We introduce \emph{conceptual views} as a formal framework grounded in Formal Concept Analysis for globally explaining neural networks. Experiments on twenty-four ImageNet models a…
Research Topic Flows in Co-Authorship Networks
Bastian Schäfermeier, Johannes Hirth, Tom Hanika
In scientometrics, scientific collaboration is often analyzed by means of co-authorships. An aspect which is often overlooked and more difficult to quantify is the flow of expertis…
Mapping Research Trajectories
Bastian Schäfermeier, Gerd Stumme, Tom Hanika
Steadily growing amounts of information, such as annually published scientific papers, have become so large that they elude an extensive manual analysis. Hence, to maintain an over…