Author name cluster

Christian Bartelt

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

13 papers

2 author rows

ECAI Conference 2025 Conference Paper

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 well-known XAI framework for unraveling decision-making processes in vision machine-learning models. The technique utilizes image segmentation methods to identify fixed regions for calculating feature importance scores as explanations. Therefore, poor segmentation can weaken the explanation and reduce the importance of segments, ultimately affecting the overall clarity of interpretation. To address these challenges, we introduce the DSEG-LIME (Data-Driven Segmentation LIME) framework, featuring: i) a data-driven segmentation for human-recognized feature generation by foundation model integration, and ii) a user-steered granularity in the hierarchical segmentation procedure through composition. Our findings demonstrate that DSEG outperforms on several XAI metrics on pretrained ImageNet models and improves the alignment of explanations with human-recognized concepts.

Details

ICML Conference 2025 Conference Paper

DCBM: Data-Efficient Visual Concept Bottleneck Models

Katharina Prasse
Patrick Knab
Sascha Marton
Christian Bartelt
Margret Keuper

Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive image corpora, limiting their effectiveness in data-sparse scenarios. We propose Data-efficient CBMs (DCBMs), which reduce the need for large sample sizes during concept generation while preserving interpretability. DCBMs define concepts as image regions detected by segmentation or detection foundation models, allowing each image to generate multiple concepts across different granularities. Exclusively containing dataset-specific concepts, DCBMs are well suited for fine-grained classification and out-of-distribution tasks. Attribution analysis using Grad-CAM demonstrates that DCBMs deliver visual concepts that can be localized in test images. By leveraging dataset-specific concepts instead of predefined or general ones, DCBMs enhance adaptability to new domains. The code is available at: https: //github. com/KathPra/DCBM.

Details

ECAI Conference 2025 Conference Paper

Disentangling Exploration of Large Language Models by Optimal Exploitation

Tim Grams
Patrick Betz
Sascha Marton
Stefan Lüdtke
Christian Bartelt

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 partially hidden state space. This work isolates exploration as the sole objective, tasking an agent with gathering information that enhances future returns. Within this framework, we argue that measuring agent returns is not sufficient for a fair evaluation. Hence, we decompose missing rewards into their exploration and exploitation components based on the optimal achievable return. Experiments with various models reveal that most struggle to explore the state space, and weak exploration is insufficient. Nevertheless, we found a positive correlation between exploration performance and reasoning capabilities. Our decomposition can provide insights into differences in behaviors driven by prompt engineering, offering a valuable tool for refining performance in exploratory tasks.

Details

ICLR Conference 2025 Conference Paper

Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization

Sascha Marton
Tim Grams
Florian Vogt
Stefan Lüdtke
Christian Bartelt
Heiner Stuckenschmidt

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 difficult to interpret. In contrast, symbolic policies allow representing decision-making strategies in a compact and interpretable way. However, learning symbolic policies directly within on-policy methods remains challenging. In this paper, we introduce SYMPOL, a novel method for SYMbolic tree-based on-POLicy RL. SYMPOL employs a tree-based model integrated with a policy gradient method, enabling the agent to learn and adapt its actions while maintaining a high level of interpretability. We evaluate SYMPOL on a set of benchmark RL tasks, demonstrating its superiority over alternative tree-based RL approaches in terms of performance and interpretability. Unlike existing methods, it enables gradient-based, end-to-end learning of interpretable, axis-aligned decision trees within standard on-policy RL algorithms. Therefore, SYMPOL can become the foundation for a new class of interpretable RL based on decision trees. Our implementation is available under: https://github.com/s-marton/sympol

Details

NeurIPS Conference 2024 Conference Paper

A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data

Andrej Tschalzev
Sascha Marton
Stefan Lüdtke
Christian Bartelt
Heiner Stuckenschmidt

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 performance differences typically have model-centered evaluation setups with overly standardized data preprocessing. This limits the external validity of these studies, as in real-world modeling pipelines, models are typically applied after dataset-specific preprocessing and feature engineering. We address this gap by proposing a data-centric evaluation framework. We select 10 relevant datasets from Kaggle competitions and implement expert-level preprocessing pipelines for each dataset. We conduct experiments with different preprocessing pipelines and hyperparameter optimization (HPO) regimes to quantify the impact of model selection, HPO, feature engineering, and test-time adaptation. Our main findings reveal: 1) After dataset-specific feature engineering, model rankings change considerably, performance differences decrease, and the importance of model selection reduces. 2) Recent models, despite their measurable progress, still significantly benefit from manual feature engineering. This holds true for both tree-based models and neural networks. 3) While tabular data is typically considered static, samples are often collected over time, and adapting to distribution shifts can be important even in supposedly static data. These insights suggest that research efforts should be directed toward a data-centric perspective, acknowledging that tabular data requires feature engineering and often exhibits temporal characteristics.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Enabling Mixed Effects Neural Networks for Diverse, Clustered Data Using Monte Carlo Methods

Andrej Tschalzev
Paul Nitschke
Lukas Kirchdorfer
Stefan Lüdtke
Christian Bartelt
Heiner Stuckenschmidt

Neural networks often assume independence among input data samples, disregarding correlations arising from inherent clustering patterns in real-world datasets (e. g. , due to different sites or repeated measurements). Recently, mixed effects neural networks (MENNs) which separate cluster-specific 'random effects' from cluster-invariant 'fixed effects' have been proposed to improve generalization and interpretability for clustered data. However, existing methods only allow for approximate quantification of cluster effects and are limited to regression and binary targets with only one clustering feature. We present MC-GMENN, a novel approach employing Monte Carlo techniques to train Generalized Mixed Effects Neural Networks. We empirically demonstrate that MC-GMENN outperforms existing mixed effects deep learning models in terms of generalization performance, time complexity, and quantification of inter-cluster variance. Additionally, MC-GMENN is applicable to a wide range of datasets, including multi-class classification tasks with multiple high-cardinality categorical features. For these datasets, we show that MC-GMENN outperforms conventional encoding and embedding methods, simultaneously offering a principled methodology for interpreting the effects of clustering patterns.

PDF Details DOI

ECAI Conference 2024 Conference Paper

Fact Probability Vector Based Goal Recognition

Nils Wilken
Lea Cohausz
Christian Bartelt
Heiner Stuckenschmidt

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 state s0. Our method maps these probabilities and observed facts into a real vector space to compute heuristic values for potential goals. These heuristic values estimate the likelihood of a given goal being the true objective of the observed agent. As obtaining exact expected probabilities for observed facts in an observation sequence is often practically infeasible, we propose and empirically validate a method for approximating these probabilities. Our empirical results show that the proposed approach offers improved goal recognition precision compared to state-of-the-art techniques while reducing computational complexity.

Details

AAAI Conference 2024 Conference Paper

GradTree: Learning Axis-Aligned Decision Trees with Gradient Descent

Sascha Marton
Stefan Lüdtke
Christian Bartelt
Heiner Stuckenschmidt

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 problem, as it is non-convex and non-differentiable. Therefore, common approaches learn DTs using a greedy growth algorithm that minimizes the impurity locally at each internal node. Unfortunately, this greedy procedure can lead to inaccurate trees. In this paper, we present a novel approach for learning hard, axis-aligned DTs with gradient descent. The proposed method uses backpropagation with a straight-through operator on a dense DT representation, to jointly optimize all tree parameters. Our approach outperforms existing methods on binary classification benchmarks and achieves competitive results for multi-class tasks. The implementation is available under: https://github.com/s-marton/GradTree

PDF Details DOI

ICLR Conference 2024 Conference Paper

GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data

Sascha Marton
Stefan Lüdtke
Christian Bartelt
Heiner Stuckenschmidt

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, there is a significant need for tabular-specific gradient-based methods due to their high flexibility. In this paper, we propose $\text{GRANDE}$, $\text{GRA}$die$\text{N}$t-Based $\text{D}$ecision Tree $\text{E}$nsembles, a novel approach for learning hard, axis-aligned decision tree ensembles using end-to-end gradient descent. GRANDE is based on a dense representation of tree ensembles, which affords to use backpropagation with a straight-through operator to jointly optimize all model parameters. Our method combines axis-aligned splits, which is a useful inductive bias for tabular data, with the flexibility of gradient-based optimization. Furthermore, we introduce an advanced instance-wise weighting that facilitates learning representations for both, simple and complex relations, within a single model. We conducted an extensive evaluation on a predefined benchmark with 19 classification datasets and demonstrate that our method outperforms existing gradient-boosting and deep learning frameworks on most datasets. The method is available under: https://github.com/s-marton/GRANDE

Details

AAMAS Conference 2024 Conference Paper

RAISE the Bar: R estriction of A ction Spaces for I mproved S ocial Welfare and E quity in Traffic Management

Michael Oesterle
Tim Grams
Christian Bartelt
Heiner Stuckenschmidt

Restriction-based governance has recently been proposed as an alternative to reward shaping for achieving system-level goals in competitive multi-agent systems. In this work, we apply these two approaches to the domain of traffic management, specifically investigating their efficacy and fairness. Our results show that edge restrictions in congested traffic networks are superior to dynamic pricing with regard to equity (i. e. , equal treatment of agents) while achieving comparable travel-time improvements. We argue that the former metric, as an adequate proxy for fairness, can be crucial for the quality and acceptance of a governance scheme, particularly when human agents are affected.

PDF

AAAI Conference 2023 Conference Paper

Online Random Feature Forests for Learning in Varying Feature Spaces

Christian Schreckenberger
Yi He
Stefan Lüdtke
Christian Bartelt
Heiner Stuckenschmidt

In this paper, we propose a new online learning algorithm tailored for data streams described by varying feature spaces (VFS), wherein new features constantly emerge and old features may stop to be observed over various time spans. Our proposed algorithm, named Online Random Feature Forests for Feature space Variabilities (ORF3V), provides a strategy to respect such feature dynamics by generating, updating, pruning, as well as online re-weighing an ensemble of what we call feature forests, which are generated and updated based on a compressed and storage efficient representation for each observed feature. We benchmark our algorithm on 12 datasets, including one novel real-world dataset of government COVID-19 responses collected through a crowd-sensing program in Spain. The empirical results substantiate the viability and effectiveness of our ORF3V algorithm and its superior accuracy performance over the state-of-the-art rival models.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

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 other hand, mixtures of exchangeable variable models (MEVMs) are a class of tractable probabilistic models that make use of exchangeability of discrete random variables to render inference tractable. Exchangeability, which arises naturally in relational domains, has not been considered for efficient representation and inference in SPNs yet. The contribution of this paper is a novel probabilistic model which we call Exchangeability-Aware Sum-Product Networks (XSPNs). It contains both SPNs and MEVMs as special cases, and combines the ability of SPNs to efficiently learn deep probabilistic models with the ability of MEVMs to efficiently handle exchangeable random variables. We introduce a structure learning algorithm for XSPNs and empirically show that they can be more accurate than conventional SPNs when the data contains repeated, interchangeable parts.

PDF Details DOI

EUMAS Conference 2021 Conference Paper

Governing Black-Box Agents in Competitive Multi-Agent Systems

Michael Pernpeintner
Christian Bartelt
Heiner Stuckenschmidt

Abstract Competitive Multi-Agent Systems (MAS) are inherently hard to control due to agent autonomy and strategic behavior, which is particularly problematic when there are system-level objectives to be achieved or specific environmental states to be avoided. Existing solutions for this task mostly assume specific knowledge about agent preferences, utilities and strategies, neglecting the fact that actions are not always directly linked to genuine agent preferences, but can also reflect anticipated competitor behavior, be a concession to a superior adversary or simply be intended to mislead other agents. This assumption both reduces applicability to real-world systems and opens room for manipulation. We therefore propose a new governance approach for competitive MAS which relies exclusively on publicly observable actions and transitions, and uses the acquired knowledge to purposefully restrict action spaces, thereby achieving the system’s objectives while preserving a high level of autonomy for the agents.

Details