Follow
Thomas Schnake
Thomas Schnake
Verified email at tu-berlin.de
Title
Cited by
Cited by
Year
Higher-order explanations of graph neural networks via relevant walks
T Schnake, O Eberle, J Lederer, S Nakajima, KT Schütt, KR Müller, ...
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
265*2021
XAI for transformers: Better explanations through conservative propagation
A Ali, T Schnake, O Eberle, G Montavon, KR Müller, L Wolf
International Conference on Machine Learning, 435-451, 2022
762022
Self-attentive, multi-context one-class classification for unsupervised anomaly detection on text
L Ruff, Y Zemlyanskiy, R Vandermeulen, T Schnake, M Kloft
Proceedings of the 57th Annual Meeting of the Association for Computational …, 2019
752019
Efficient computation of higher-order subgraph attribution via message passing
P Xiong, T Schnake, G Montavon, KR Müller, S Nakajima
International Conference on Machine Learning, 24478-24495, 2022
52022
Relevant walk search for explaining graph neural networks
P Xiong, T Schnake, M Gastegger, G Montavon, KR Muller, S Nakajima
International Conference on Machine Learning, 38301-38324, 2023
12023
Efficient Higher-Order Subgraph Attribution via Message Passing
P Xiong, T Schnake, G Montavon, KR Müller, S Nakajima
MA thesis. Technische Universität Berlin, 2022
12022
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology
J Hense, MJ Idaji, O Eberle, T Schnake, J Dippel, L Ciernik, O Buchstab, ...
arXiv preprint arXiv:2406.04280, 2024
2024
Synthesis of High-Resolution Load Profiles with Minimal Data
T Schnake, D Bauer
arXiv preprint arXiv:1903.06625, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–8