activity
20242026
collaborators

9 papers

cs.LG2026

RelShap: Relationally Consistent Shapley Explanations

Seungeun Lee, Joao Fonseca, Julia Stoyanovich

Machine learning pipelines commonly flatten relational data into single-table representations, discarding structural constraints. Widely used Shapley value-based feature attributio…

cs.LG2026

ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations

Joao Fonseca, Julia Stoyanovich

Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predi…

cs.AI2025

ShaRP: Explaining Rankings and Preferences with Shapley Values

Venetia Pliatsika, Joao Fonseca, Kateryna Akhynko +2

Algorithmic decisions in critical domains such as hiring, college admissions, and lending are often based on rankings. Given the impact of these decisions on individuals, organizat…

cs.AI2025

Still More Shades of Null: An Evaluation Suite for Responsible Missing Value Imputation

Falaah Arif Khan, Denys Herasymuk, Nazar Protsiv +1

Data missingness is a practical challenge of sustained interest to the scientific community. In this paper, we present Shades-of-Null, an evaluation suite for responsible missing v…

cs.LG2025

VirnyFlow: Optimizing ML Pipelines for Accuracy, Fairness, and Stability at Scale

Denys Herasymuk, Nazar Protsiv, Anastasiia Mozghova +2

Developing machine learning (ML) systems for real-world deployment requires navigating context-dependent trade-offs among accuracy, fairness, stability, and other objectives. Exist…

cs.LG2025

SHAP-based Explanations are Sensitive to Feature Representation

Hyunseung Hwang, Andrew Bell, Joao Fonseca +3

Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representatio…