53 citations · 107 across the 20 of their papers we have counts for
20 papers
ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation
David Rundel, Fabian Fumagalli, Maximilian Muschalik +2
Shapley values are a principled attribution measure widely used in interpretable machine learning, but their exact computation scales exponentially with the number of players, moti…
Proxy-Based Approximation of Shapley and Banzhaf Interactions
Santo M. A. R. Thies, Hubert Baniecki, R. Teal Witter +3
Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trad…
The Metagame of Interpretability and Meta-Attributions
Hubert Baniecki, Przemyslaw Biecek, Fabian Fumagalli
How can an arbitrary attribution method be generalized from first principles to capture interactions? We answer this with the metagame, a conceptual framework for quantifying secon…
An Odd Estimator for Shapley Values
Fabian Fumagalli, Landon Butler, Justin Singh Kang +2
The Shapley value is a ubiquitous framework for attribution in machine learning, encompassing feature importance, data valuation, and causal inference. However, its exact computati…
GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations
Julia Herbinger, Gabriel Laberge, Maximilian Muschalik +3
Feature-based explanation methods aim to quantify how features influence the model's behavior, either locally or globally, but different methods often disagree, producing conflicti…
PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
Fabian Fumagalli, R. Teal Witter, Christopher Musco
Shapley values have emerged as a central game-theoretic tool in explainable AI (XAI). However, computing Shapley values exactly requires game evaluations for a model with …
Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions
Hubert Baniecki, Maximilian Muschalik, Fabian Fumagalli +3
Language-image pre-training (LIP) enables the development of vision-language models capable of zero-shot classification, localization, multimodal retrieval, and semantic understand…
Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection
Maximilian Spliethöver, Tim Knebler, Fabian Fumagalli +4
Recent advances on instruction fine-tuning have led to the development of various prompting techniques for large language models, such as explicit reasoning steps. However, the suc…
HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization
Marcel Wever, Maximilian Muschalik, Fabian Fumagalli +1
Hyperparameter optimization (HPO) is a crucial step in achieving strong predictive performance. Yet, the impact of individual hyperparameters on model generalization is highly cont…
Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks
Maximilian Muschalik, Fabian Fumagalli, Paolo Frazzetto +5
Albeit the ubiquitous use of Graph Neural Networks (GNNs) in machine learning (ML) prediction tasks involving graph-structured data, their interpretability remains challenging. In…
Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory
Fabian Fumagalli, Maximilian Muschalik, Eyke Hüllermeier +2
Feature-based explanations, using perturbations or gradients, are a prevalent tool to understand decisions of black box machine learning models. Yet, differences between these meth…
shapiq: Shapley Interactions for Machine Learning
Maximilian Muschalik, Hubert Baniecki, Fabian Fumagalli +3
Originally rooted in game theory, the Shapley Value (SV) has recently become an important tool in machine learning research. Perhaps most notably, it is used for feature attributio…
No learning rates needed: Introducing SALSA -- Stable Armijo Line Search Adaptation
Philip Kenneweg, Tristan Kenneweg, Fabian Fumagalli +1
In recent studies, line search methods have been demonstrated to significantly enhance the performance of conventional stochastic gradient descent techniques across various dataset…
KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions
Fabian Fumagalli, Maximilian Muschalik, Patrick Kolpaczki +2
The Shapley value (SV) is a prevalent approach of allocating credit to machine learning (ML) entities to understand black box ML models. Enriching such interpretations with higher-…
SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratification
Patrick Kolpaczki, Maximilian Muschalik, Fabian Fumagalli +2
Addressing the limitations of individual attribution scores via the Shapley value (SV), the field of explainable AI (XAI) has recently explored intricate interactions of features o…
Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles
Maximilian Muschalik, Fabian Fumagalli, Barbara Hammer +1
While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving t…
iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios
Maximilian Muschalik, Fabian Fumagalli, Rohit Jagtani +2
Post-hoc explanation techniques such as the well-established partial dependence plot (PDP), which investigates feature dependencies, are used in explainable artificial intelligence…
iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams
Maximilian Muschalik, Fabian Fumagalli, Barbara Hammer +1
Existing methods for explainable artificial intelligence (XAI), including popular feature importance measures such as SAGE, are mostly restricted to the batch learning scenario. Ho…
SHAP-IQ: Unified Approximation of any-order Shapley Interactions
Fabian Fumagalli, Maximilian Muschalik, Patrick Kolpaczki +2
Predominately in explainable artificial intelligence (XAI) research, the Shapley value (SV) is applied to determine feature attributions for any black box model. Shapley interactio…
Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams
Fabian Fumagalli, Maximilian Muschalik, Eyke Hüllermeier +1
Explainable Artificial Intelligence (XAI) has mainly focused on static learning scenarios so far. We are interested in dynamic scenarios where data is sampled progressively, and le…