Thomas Schnake

15 papers A* 4Journal 8Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology.
CoRR
Mina Jamshidi Idaji, Julius Hense, Tom Neuhäuser, Augustin Krause, Yanqing Luo, Oliver Eberle, Thomas Schnake, Laure Ciernik, Farnoush Rezaei Jafari, Reza Vahidimajd, Jonas Dippel, Christoph Walz, Frederick Klauschen, Andreas Mock, Klaus-Robert Müller
2025 — —
Developing model-aligned and human-readable explanations for artificial intelligence.
Thomas Schnake
2025 J jnl
Towards symbolic XAI - explanation through human understandable logical relationships between features.
Inf. Fusion
Thomas Schnake, Farnoush Rezaei Jafari, Jonas Lederer, Ping Xiong, Shinichi Nakajima, Stefan Gugler, Grégoire Montavon, Klaus-Robert Müller
2025 — conf
Uncovering the Structure of Explanation Quality with Spectral Analysis.
xAI (3)
Johannes Maeß, Grégoire Montavon, Shinichi Nakajima, Klaus-Robert Müller, Thomas Schnake
2025 J jnl
Uncovering the Structure of Explanation Quality with Spectral Analysis.
CoRR
Johannes Maeß, Grégoire Montavon, Shinichi Nakajima, Klaus-Robert Müller, Thomas Schnake
2024 J jnl
Towards Symbolic XAI - Explanation Through Human Understandable Logical Relationships Between Features.
CoRR
Thomas Schnake, Farnoush Rezaei Jafari, Jonas Lederer, Ping Xiong, Shinichi Nakajima, Stefan Gugler, Grégoire Montavon, Klaus-Robert Müller
2024 A* conf
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology.
NeurIPS
Julius Hense, Mina Jamshidi Idaji, Oliver Eberle, Thomas Schnake, Jonas Dippel, Laure Ciernik, Oliver Buchstab, Andreas Mock, Frederick Klauschen, Klaus-Robert Müller
2024 J jnl
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology.
CoRR
Julius Hense, Mina Jamshidi Idaji, Oliver Eberle, Thomas Schnake, Jonas Dippel, Laure Ciernik, Oliver Buchstab, Andreas Mock, Frederick Klauschen, Klaus-Robert Müller
2023 A* conf
Relevant Walk Search for Explaining Graph Neural Networks.
ICML
Ping Xiong, Thomas Schnake, Michael Gastegger, Grégoire Montavon, Klaus-Robert Müller, Shinichi Nakajima
2022 A* conf
Efficient Computation of Higher-Order Subgraph Attribution via Message Passing.
ICML
Ping Xiong, Thomas Schnake, Grégoire Montavon, Klaus-Robert Müller, Shinichi Nakajima
2022 J jnl
Higher-Order Explanations of Graph Neural Networks via Relevant Walks.
IEEE Trans. Pattern Anal. Mach. Intell.
Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schütt, Klaus-Robert Müller, Grégoire Montavon
2022 A* conf
XAI for Transformers: Better Explanations through Conservative Propagation.
ICML
Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, Lior Wolf
2022 J jnl
XAI for Transformers: Better Explanations through Conservative Propagation.
CoRR
Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, Lior Wolf
2020 J jnl
XAI for Graphs: Explaining Graph Neural Network Predictions by Identifying Relevant Walks.
CoRR
Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schütt, Klaus-Robert Müller, Grégoire Montavon
2019 — conf
Self-Attentive, Multi-Context One-Class Classification for Unsupervised Anomaly Detection on Text.
ACL (1)
Lukas Ruff, Yury Zemlyanskiy, Robert A. Vandermeulen, Thomas Schnake, Marius Kloft