Publications (14)
Reasoning on Knowledge Graphs with Debate Dynamics
Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma +3
We propose a novel method for automatic reasoning on knowledge graphs based on debate dynamics. The main idea is to frame the task of triple classification as a debate game between…
Combining Sub-Symbolic and Symbolic Methods for Explainability
Anna Himmelhuber, Stephan Grimm, Sonja Zillner +3
Similarly to other connectionist models, Graph Neural Networks (GNNs) lack transparency in their decision-making. A number of sub-symbolic approaches have been developed to provide…
In Search of Socio-Technical Congruence: A Large-Scale Longitudinal Study
Wolfgang Mauerer, Mitchell Joblin, Damian A. Tamburri +3
We report on a large-scale empirical study investigating the relevance of socio-technical congruence over key basic software quality metrics, namely, bugs and churn. In particular,…
Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs
Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma +3
We propose a novel method for fact-checking on knowledge graphs based on debate dynamics. The underlying idea is to frame the task of triple classification as a debate game between…
Learning Domain-Specific Edit Operations from Model Repositories with Frequent Subgraph Mining
Christof Tinnes, Timo Kehrer, Mitchell Joblin +3
Model transformations play a fundamental role in model-driven software development. They can be used to solve or support central tasks, such as creating models, handling model co-e…
Demystifying Graph Neural Network Explanations
Anna Himmelhuber, Mitchell Joblin, Martin Ringsquandl +1
Graph neural networks (GNNs) are quickly becoming the standard approach for learning on graph structured data across several domains, but they lack transparency in their decision-m…
Integrating Logical Rules Into Neural Multi-Hop Reasoning for Drug Repurposing
Yushan Liu, Marcel Hildebrandt, Mitchell Joblin +2
The graph structure of biomedical data differs from those in typical knowledge graph benchmark tasks. A particular property of biomedical data is the presence of long-range depende…
Classifying Developers into Core and Peripheral: An Empirical Study on Count and Network Metrics
Mitchell Joblin, Sven Apel, Claus Hunsen +1
Knowledge about the roles developers play in a software project is crucial to understanding the project's collaborative dynamics. Developers are often classified according to the d…
Generating Table Vector Representations
Aneta Koleva, Martin Ringsquandl, Mitchell Joblin +1
High-quality Web tables are rich sources of information that can be used to populate Knowledge Graphs (KG). The focus of this paper is an evaluation of methods for table-to-class a…
On Calibration of Graph Neural Networks for Node Classification
Tong Liu, Yushan Liu, Marcel Hildebrandt +3
Graphs can model real-world, complex systems by representing entities and their interactions in terms of nodes and edges. To better exploit the graph structure, graph neural networ…
Power to the Relational Inductive Bias: Graph Neural Networks in Electrical Power Grids
Martin Ringsquandl, Houssem Sellami, Marcel Hildebrandt +4
The application of graph neural networks (GNNs) to the domain of electrical power grids has high potential impact on smart grid monitoring. Even though there is a natural correspon…
Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphs
Yushan Liu, Marcel Hildebrandt, Mitchell Joblin +3
Biomedical knowledge graphs permit an integrative computational approach to reasoning about biological systems. The nature of biological data leads to a graph structure that differ…
Evolutionary Trends of Developer Coordination: A Network Approach
Mitchell Joblin, Sven Apel, Wolfgang Mauerer
Software evolution is a fundamental process that transcends the realm of technical artifacts and permeates the entire organizational structure of a software project. By means of a…
TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs
Yushan Liu, Yunpu Ma, Marcel Hildebrandt +2
Conventional static knowledge graphs model entities in relational data as nodes, connected by edges of specific relation types. However, information and knowledge evolve continuous…