no code implementations • ICLR 2022 • Mattia Rigotti, Christoph Miksovic, Ioana Giurgiu, Thomas Gschwind, Paolo Scotton
In particular, we design the Concept Transformer, a deep learning module that exposes explanations of the output of a model in which it is embedded in terms of attention over user-defined high-level concepts.
no code implementations • 14 Feb 2021 • Nasrullah Sheikh, Xiao Qin, Berthold Reinwald, Christoph Miksovic, Thomas Gschwind, Paolo Scotton
Knowledge graph embedding methods learn embeddings of entities and relations in a low dimensional space which can be used for various downstream machine learning tasks such as link prediction and entity matching.
no code implementations • 19 Jul 2019 • Thomas Gschwind, Christoph Miksovic, Julian Minder, Katsiaryna Mirylenka, Paolo Scotton
These insights guide further analytic approaches to the data and support data visualization.