3 citations · 8 across the 19 of their papers we have counts for
19 papers
Which LIME should I trust? Concepts, Challenges, and Solutions
Patrick Knab, Sascha Marton, Udo Schlegel +1
As neural networks become dominant in essential systems, Explainable Artificial Intelligence (XAI) plays a crucial role in fostering trust and detecting potential misbehavior of op…
Unreflected Use of Tabular Data Repositories Can Undermine Research Quality
Andrej Tschalzev, Lennart Purucker, Stefan Lüdtke +3
Data repositories have accumulated a large number of tabular datasets from various domains. Machine Learning researchers are actively using these datasets to evaluate novel approac…
Disentangling Exploration of Large Language Models by Optimal Exploitation
Tim Grams, Patrick Betz, Sascha Marton +2
Exploration is a crucial skill for in-context reinforcement learning in unknown environments. However, it remains unclear if large language models can effectively explore a partial…
A*Net and NBFNet Learn Negative Patterns on Knowledge Graphs
Patrick Betz, Nathanael Stelzner, Christian Meilicke +2
In this technical report, we investigate the predictive performance differences of a rule-based approach and the GNN architectures NBFNet and A*Net with respect to knowledge graph…
DCBM: Data-Efficient Visual Concept Bottleneck Models
Katharina Prasse, Patrick Knab, Sascha Marton +2
Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on con…
Interpreting Outliers in Time Series Data through Decoding Autoencoder
Patrick Knab, Sascha Marton, Christian Bartelt +1
Outlier detection is a crucial analytical tool in various fields. In critical systems like manufacturing, malfunctioning outlier detection can be costly and safety-critical. Theref…
Fact Probability Vector Based Goal Recognition
Nils Wilken, Lea Cohausz, Christian Bartelt +1
We present a new approach to goal recognition that involves comparing observed facts with their expected probabilities. These probabilities depend on a specified goal g and initial…
Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization
Sascha Marton, Tim Grams, Florian Vogt +3
Reinforcement learning (RL) has seen significant success across various domains, but its adoption is often limited by the black-box nature of neural network policies, making them d…
A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
Andrej Tschalzev, Sascha Marton, Stefan Lüdtke +2
Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing…
Enabling Mixed Effects Neural Networks for Diverse, Clustered Data Using Monte Carlo Methods
Andrej Tschalzev, Paul Nitschke, Lukas Kirchdorfer +3
Neural networks often assume independence among input data samples, disregarding correlations arising from inherent clustering patterns in real-world datasets (e.g., due to differe…
Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models
Patrick Knab, Sascha Marton, Christian Bartelt
LIME (Local Interpretable Model-agnostic Explanations) is a popular XAI framework for unraveling decision-making processes in vision machine-learning models. The technique utilizes…
GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data
Sascha Marton, Stefan Lüdtke, Christian Bartelt +1
Despite the success of deep learning for text and image data, tree-based ensemble models are still state-of-the-art for machine learning with heterogeneous tabular data. However, t…
Planning Landmark Based Goal Recognition Revisited: Does Using Initial State Landmarks Make Sense?
Nils Wilken, Lea Cohausz, Christian Bartelt +1
Goal recognition is an important problem in many application domains (e.g., pervasive computing, intrusion detection, computer games, etc.). In many application scenarios, it is im…
GradTree: Learning Axis-Aligned Decision Trees with Gradient Descent
Sascha Marton, Stefan Lüdtke, Christian Bartelt +1
Decision Trees (DTs) are commonly used for many machine learning tasks due to their high degree of interpretability. However, learning a DT from data is a difficult optimization pr…
Leveraging Planning Landmarks for Hybrid Online Goal Recognition
Nils Wilken, Lea Cohausz, Johannes Schaum +3
Goal recognition is an important problem in many application domains (e.g., pervasive computing, intrusion detection, computer games, etc.). In many application scenarios it is imp…
Outlier Explanation via Sum-Product Networks
Stefan Lüdtke, Christian Bartelt, Heiner Stuckenschmidt
Outlier explanation is the task of identifying a set of features that distinguish a sample from normal data, which is important for downstream (human) decision-making. Existing met…
Explaining Neural Networks without Access to Training Data
Sascha Marton, Stefan Lüdtke, Christian Bartelt +2
We consider generating explanations for neural networks in cases where the network's training data is not accessible, for instance due to privacy or safety issues. Recently, $\math…
Exchangeability-Aware Sum-Product Networks
Stefan Lüdtke, Christian Bartelt, Heiner Stuckenschmidt
Sum-Product Networks (SPNs) are expressive probabilistic models that provide exact, tractable inference. They achieve this efficiency by making use of local independence. On the ot…
xRAI: Explainable Representations through AI
Christiann Bartelt, Sascha Marton, Heiner Stuckenschmidt
We present xRAI an approach for extracting symbolic representations of the mathematical function a neural network was supposed to learn from the trained network. The approach is ba…