167 citations · 557 across the 21 of their papers we have counts for
21 papers
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…
Interpreting CLIP with Hierarchical Sparse Autoencoders
Vladimir Zaigrajew, Hubert Baniecki, Przemyslaw Biecek
Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal represent…
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…
Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models
Maciej Chrabaszcz, Hubert Baniecki, Piotr Komorowski +2
Analysis of 3D segmentation models, especially in the context of medical imaging, is often limited to segmentation performance metrics that overlook the crucial aspect of explainab…
Efficient and Accurate Explanation Estimation with Distribution Compression
Hubert Baniecki, Giuseppe Casalicchio, Bernd Bischl +1
We discover a theoretical connection between explanation estimation and distribution compression that significantly improves the approximation of feature attributions, importance,…
On the Robustness of Global Feature Effect Explanations
Hubert Baniecki, Giuseppe Casalicchio, Bernd Bischl +1
We study the robustness of global post-hoc explanations for predictive models trained on tabular data. Effects of predictor features in black-box supervised learning are an essenti…
Red-Teaming Segment Anything Model
Krzysztof Jankowski, Bartlomiej Sobieski, Mateusz Kwiatkowski +4
Foundation models have emerged as pivotal tools, tackling many complex tasks through pre-training on vast datasets and subsequent fine-tuning for specific applications. The Segment…
Red Teaming Models for Hyperspectral Image Analysis Using Explainable AI
Vladimir Zaigrajew, Hubert Baniecki, Lukasz Tulczyjew +4
Remote sensing (RS) applications in the space domain demand machine learning (ML) models that are reliable, robust, and quality-assured, making red teaming a vital approach for ide…
Interpretable Machine Learning for Survival Analysis
Sophie Hanna Langbein, Mateusz Krzyziński, Mikołaj Spytek +3
With the spread and rapid advancement of black box machine learning models, the field of interpretable machine learning (IML) or explainable artificial intelligence (XAI) has becom…
Be Careful When Evaluating Explanations Regarding Ground Truth
Hubert Baniecki, Maciej Chrabaszcz, Andreas Holzinger +3
Evaluating explanations of image classifiers regarding ground truth, e.g. segmentation masks defined by human perception, primarily evaluates the quality of the models under consid…
survex: an R package for explaining machine learning survival models
Mikołaj Spytek, Mateusz Krzyziński, Sophie Hanna Langbein +3
Due to their flexibility and superior performance, machine learning models frequently complement and outperform traditional statistical survival models. However, their widespread a…
Explaining and visualizing black-box models through counterfactual paths
Bastian Pfeifer, Mateusz Krzyzinski, Hubert Baniecki +3
Explainable AI (XAI) is an increasingly important area of machine learning research, which aims to make black-box models transparent and interpretable. In this paper, we propose a…
Adversarial attacks and defenses in explainable artificial intelligence: A survey
Hubert Baniecki, Przemyslaw Biecek
Explainable artificial intelligence (XAI) methods are portrayed as a remedy for debugging and trusting statistical and deep learning models, as well as interpreting their predictio…
Towards Evaluating Explanations of Vision Transformers for Medical Imaging
Piotr Komorowski, Hubert Baniecki, Przemysław Biecek
As deep learning models increasingly find applications in critical domains such as medical imaging, the need for transparent and trustworthy decision-making becomes paramount. Many…
Interpretable machine learning for time-to-event prediction in medicine and healthcare
Hubert Baniecki, Bartlomiej Sobieski, Patryk Szatkowski +2
Time-to-event prediction, e.g. cancer survival analysis or hospital length of stay, is a highly prominent machine learning task in medical and healthcare applications. However, onl…
Performance is not enough: the story told by a Rashomon quartet
Przemyslaw Biecek, Hubert Baniecki, Mateusz Krzyzinski +1
The usual goal of supervised learning is to find the best model, the one that optimizes a particular performance measure. However, what if the explanation provided by this model is…
SurvSHAP(t): Time-dependent explanations of machine learning survival models
Mateusz Krzyziński, Mikołaj Spytek, Hubert Baniecki +1
Machine and deep learning survival models demonstrate similar or even improved time-to-event prediction capabilities compared to classical statistical learning methods yet are too…
Graph-guided random forest for gene set selection
Bastian Pfeifer, Hubert Baniecki, Anna Saranti +2
Machine learning methods can detect complex relationships between variables, but usually do not exploit domain knowledge. This is a limitation because in many scientific discipline…
Fooling Partial Dependence via Data Poisoning
Hubert Baniecki, Wojciech Kretowicz, Przemyslaw Biecek
Many methods have been developed to understand complex predictive models and high expectations are placed on post-hoc model explainability. It turns out that such explanations are…
dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python
Hubert Baniecki, Wojciech Kretowicz, Piotr Piatyszek +2
The increasing amount of available data, computing power, and the constant pursuit for higher performance results in the growing complexity of predictive models. Their black-box na…
The Grammar of Interactive Explanatory Model Analysis
Hubert Baniecki, Dariusz Parzych, Przemyslaw Biecek
The growing need for in-depth analysis of predictive models leads to a series of new methods for explaining their local and global properties. Which of these methods is the best? I…