268 citations · 323 across the 12 of their papers we have counts for
15 papers
Revisiting Explainable AI through Model-Independent Concept Dictionaries
Thomas Schnake, Doreen Schöppenthau, Alexander Meyer +3
Modern applications of AI rely on increasingly complex models. Explainable AI (XAI) has emerged as a set of techniques aimed at improving model transparency. However, existing XAI…
Explaining Hyperbolic Neural Networks via Geometry-Aware Relevance Propagation
Ping Xiong, Shanglin Li, Yi Ding +2
Hyperbolic neural networks introduce geometric operations that require explicit treatment in relevance propagation. Equivalent geometric realizations can produce different feature…
Explaining Temporal Graph Neural Networks via Feature-induced Information Flow
Ping Xiong, Thomas Schnake, Klaus-Robert Müller +1
Event-based Temporal Graph Neural Networks (ETGNNs) have demonstrated strong performance across a wide range of applications, including social network analysis, epidemic tracing, r…
Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology
Yanqing Luo, Julius Hense, Niklas Prenißl +4
Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology. Existing methods primarily rely on heatmaps that hig…
Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures
Ping Xiong, Thomas Schnake, Grégoire Montavon +2
To understand how a neural network (NN) functions and makes predictions, it has become increasingly clear that analyzing only the input domain is insufficient -- one must also exam…
Relevant Walk Search for Explaining Graph Neural Networks
Ping Xiong, Thomas Schnake, Michael Gastegger +3
Graph Neural Networks (GNNs) have become important machine learning tools for graph analysis, and its explainability is crucial for safety, fairness, and robustness. Layer-wise rel…
Efficient Higher-order Subgraph Attribution via Message Passing
Ping Xiong, Thomas Schnake, Grégoire Montavon +2
Explaining graph neural networks (GNNs) has become more and more important recently. Higher-order interpretation schemes, such as GNN-LRP (layer-wise relevance propagation for GNN)…
Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology
Mina Jamshidi Idaji, Julius Hense, Tom Neuhäuser +12
Multiple instance learning (MIL) has enabled substantial progress in computational histopathology, where a large amount of patches from gigapixel whole slide images are aggregated…
Uncovering the Structure of Explanation Quality with Spectral Analysis
Johannes Maeß, Grégoire Montavon, Shinichi Nakajima +2
As machine learning models are increasingly considered for high-stakes domains, effective explanation methods are crucial to ensure that their prediction strategies are transparent…
Analyzing Atomic Interactions in Molecules as Learned by Neural Networks
Malte Esders, Thomas Schnake, Jonas Lederer +4
While machine learning (ML) models have been able to achieve unprecedented accuracies across various prediction tasks in quantum chemistry, it is now apparent that accuracy on a te…
Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
Thomas Schnake, Farnoush Rezaei Jafari, Jonas Lederer +5
Explainable Artificial Intelligence (XAI) plays a crucial role in fostering transparency and trust in AI systems, where traditional XAI approaches typically offer one level of abst…
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology
Julius Hense, Mina Jamshidi Idaji, Oliver Eberle +7
Multiple instance learning (MIL) is an effective and widely used approach for weakly supervised machine learning. In histopathology, MIL models have achieved remarkable success in…
XAI for Transformers: Better Explanations through Conservative Propagation
Ameen Ali, Thomas Schnake, Oliver Eberle +3
Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transpar…
Higher-Order Explanations of Graph Neural Networks via Relevant Walks
Thomas Schnake, Oliver Eberle, Jonas Lederer +4
Graph Neural Networks (GNNs) are a popular approach for predicting graph structured data. As GNNs tightly entangle the input graph into the neural network structure, common explain…
Synthesis of High-Resolution Load Profiles with Minimal Data
Thomas Schnake, David Bauer
For the estimation of a new energy supply system it is an important to have high-resolution energy load profile. Such a profile is in general either not present or very costly to o…