no code implementations • 23 Dec 2022 • Vadim Borisov, Gjergji Kasneci
The majority of existing post-hoc explanation approaches for machine learning models produce independent, per-variable feature attribution scores, ignoring a critical inherent characteristics of homogeneously structured data, such as visual or text data: there exist latent inter-variable relationships between features.
1 code implementation • 12 Oct 2022 • Vadim Borisov, Kathrin Seßler, Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci
Tabular data is among the oldest and most ubiquitous forms of data.
1 code implementation • 5 Aug 2022 • Michael Gröger, Vadim Borisov, Gjergji Kasneci
One of the core challenges facing the medical image computing community is fast and efficient data sample labeling.
1 code implementation • 1 Feb 2022 • Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, Enkelejda Kasneci
With a variety of local feature attribution methods being proposed in recent years, follow-up work suggested several evaluation strategies.
1 code implementation • 14 Nov 2021 • Vadim Borisov, Johannes Meier, Johan van den Heuvel, Hamed Jalali, Gjergji Kasneci
Understanding the results of deep neural networks is an essential step towards wider acceptance of deep learning algorithms.
2 code implementations • 5 Oct 2021 • Vadim Borisov, Tobias Leemann, Kathrin Seßler, Johannes Haug, Martin Pawelczyk, Gjergji Kasneci
Moreover, we discuss deep learning approaches for generating tabular data, and we also provide an overview over strategies for explaining deep models on tabular data.
no code implementations • 29 Sep 2021 • Vadim Borisov, Klaus Broelemann, Enkelejda Kasneci, Gjergji. Kasneci
Although deep neural networks (DNNs) constitute the state-of-the-art in many tasks based on image, audio, or text data, their performance on heterogeneous, tabular data is typically inferior to that of decision tree ensembles.
no code implementations • 29 Oct 2020 • Nikolaos Nikolaou, Ingo P. Waldmann, Angelos Tsiaras, Mario Morvan, Billy Edwards, Kai Hou Yip, Giovanna Tinetti, Subhajit Sarkar, James M. Dawson, Vadim Borisov, Gjergji Kasneci, Matej Petkovic, Tomaz Stepisnik, Tarek Al-Ubaidi, Rachel Louise Bailey, Michael Granitzer, Sahib Julka, Roman Kern, Patrick Ofner, Stefan Wagner, Lukas Heppe, Mirko Bunse, Katharina Morik
For instance, the most prolific method for detecting exoplanets and inferring several of their characteristics, transit photometry, is very sensitive to the presence of stellar spots.