Thomas Schnake

According to our database, Thomas Schnake authored at least 6 papers between 2019 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Relevant Walk Search for Explaining Graph Neural Networks.

Ping Xiong, Thomas Schnake, Michael Gastegger, Grégoire Montavon, Klaus-Robert Müller, Shinichi Nakajima

Proceedings of the International Conference on Machine Learning, 2023

2022

Higher-Order Explanations of Graph Neural Networks via Relevant Walks.

Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schütt, Klaus-Robert Müller, Grégoire Montavon

IEEE Trans. Pattern Anal. Mach. Intell., 2022

Efficient Computation of Higher-Order Subgraph Attribution via Message Passing.

Ping Xiong, Thomas Schnake, Grégoire Montavon, Klaus-Robert Müller, Shinichi Nakajima

Proceedings of the International Conference on Machine Learning, 2022

XAI for Transformers: Better Explanations through Conservative Propagation.

Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, Lior Wolf

Proceedings of the International Conference on Machine Learning, 2022

2020

XAI for Graphs: Explaining Graph Neural Network Predictions by Identifying Relevant Walks.

Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schütt, Klaus-Robert Müller, Grégoire Montavon

CoRR, 2020

2019

Self-Attentive, Multi-Context One-Class Classification for Unsupervised Anomaly Detection on Text.

Lukas Ruff, Yury Zemlyanskiy, Robert A. Vandermeulen, Thomas Schnake, Marius Kloft

Proceedings of the 57th Conference of the Association for Computational Linguistics, 2019