Thomas Schnake
5 papers · 2019–2024 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
layer-wise relevance propagation
(3)
graph neural network
(2)
explainable ai
(1)
feature attribution
(1)
model interpretability
(1)
multiple instance learning
(1)
message passing
(1)
max-product algorithm
(1)
probabilistic graphical model
(1)
attention head
(1)
unsupervised anomaly detection
(1)
layer normalization
(1)
gradient propagation
(1)
one-class classification
(1)
walk search
(1)
subgraph attribution
(1)
gnn explanation
(1)
higher-order interpretation
(1)
text anomaly detection
(1)
biomarker prediction
(1)
Papers
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology
NeurIPS 2024
Relevant Walk Search for Explaining Graph Neural Networks
ICML 2023
Efficient Computation of Higher-Order Subgraph Attribution via Message Passing
ICML 2022
XAI for Transformers: Better Explanations through Conservative Propagation
ICML 2022
Self-Attentive, Multi-Context One-Class Classification for Unsupervised Anomaly Detection on Text
ACL 2019