1 code implementation • 3 Jun 2022 • Tong Liu, Yushan Liu, Marcel Hildebrandt, Mitchell Joblin, Hang Li, Volker Tresp
We investigate the calibration of graph neural networks for node classification, study the effect of existing post-processing calibration methods, and analyze the influence of model capacity, graph density, and a new loss function on calibration.
1 code implementation • 15 Dec 2021 • Yushan Liu, Yunpu Ma, Marcel Hildebrandt, Mitchell Joblin, Volker Tresp
Conventional static knowledge graphs model entities in relational data as nodes, connected by edges of specific relation types.
no code implementations • 3 Dec 2021 • Anna Himmelhuber, Stephan Grimm, Sonja Zillner, Mitchell Joblin, Martin Ringsquandl, Thomas Runkler
Similarly to other connectionist models, Graph Neural Networks (GNNs) lack transparency in their decision-making.
no code implementations • 25 Nov 2021 • Anna Himmelhuber, Mitchell Joblin, Martin Ringsquandl, Thomas Runkler
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-making.
no code implementations • 28 Oct 2021 • Aneta Koleva, Martin Ringsquandl, Mitchell Joblin, Volker Tresp
High-quality Web tables are rich sources of information that can be used to populate Knowledge Graphs (KG).
no code implementations • 8 Sep 2021 • Martin Ringsquandl, Houssem Sellami, Marcel Hildebrandt, Dagmar Beyer, Sylwia Henselmeyer, Sebastian Weber, Mitchell Joblin
The application of graph neural networks (GNNs) to the domain of electrical power grids has high potential impact on smart grid monitoring.
1 code implementation • 18 Mar 2021 • Yushan Liu, Marcel Hildebrandt, Mitchell Joblin, Martin Ringsquandl, Rime Raissouni, Volker Tresp
Biomedical knowledge graphs permit an integrative computational approach to reasoning about biological systems.
no code implementations • 10 Jul 2020 • Yushan Liu, Marcel Hildebrandt, Mitchell Joblin, Martin Ringsquandl, Volker Tresp
The graph structure of biomedical data differs from those in typical knowledge graph benchmark tasks.
no code implementations • 9 Jan 2020 • Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma, Martin Ringsquandl, Mitchell Joblin, Volker Tresp
The underlying idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to justify the fact being true (thesis) or the fact being false (antithesis), respectively.
2 code implementations • 2 Jan 2020 • Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma, Martin Ringsquandl, Mitchell Joblin, Volker Tresp
The main idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to promote the fact being true (thesis) or the fact being false (antithesis), respectively.