Ignacy Stepka

I am currently working as a research assistant at Carnegie Mellon University under Dr. Artur Dubrawski in AutonLab . My research focuses on adaptive strategies for handling persistent agent failures in decentralized federated learning. Previously, I worked on the formal verification of Bayesian Networks to ensure AI systems meet critical design specifications. Additionally, I contributed to the DARPA Triage Challenge, helping develop a Bayesian Network prototype in collaboration with medical experts to autonomously perform triage during mass casualty incidents.

I also work as a research assistant at the Machine Learning Laboratory, Poznan University of Technology, under Prof. Jerzy Stefanowski and Dr. Mateusz Lango. My research focuses on developing robust counterfactual explanations to enhance the interpretability of black-box models in dynamic environments. Currently, I am designing a statistical approach to generate explanations that remain reliable despite model changes, making them more actionable for end-users.

Previously, I was part of the R&D team at the Poznan Supercomputing and Networking Center (Polish Academy of Sciences), contributing to various EU-funded projects since 2021. My work involved analyzing black-box model behavior and implementing anomaly detection solutions in industrial automotive settings and HPC clusters.

news

Nov 17, 2024	Paper accepted at SIGKDD'25 main track
Nov 10, 2024	Three posters at ML in PL in Warsaw, Poland
Sep 13, 2024	Oral presentation at XRAI workshop on ECML PKDD 2024 in Vilnus, Lithuania
May 04, 2024	Poster at GhostDay AMLC in Poznan, Poland
Apr 24, 2023	Poster at 4-th Polish Conference on Artificial Intelligence in Lodz, Poland

selected publications

Conference
Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change

Ignacy Stępka, Mateusz Lango, and Jerzy Stefanowski

In 31st SIGKDD Conference on Knowledge Discovery and Data Mining - Research Track, 2025

Abs DOI arXiv Bib Supp Code Website

Counterfactual explanations (CFEs) guide users on how to adjust inputs to machine learning models to achieve desired outputs. While existing research primarily addresses static scenarios, real-world applications often involve data or model changes, potentially invalidating previously generated CFEs and rendering user-induced input changes ineffective. Current methods addressing this issue often support only specific models or change types, require extensive hyperparameter tuning, or fail to provide probabilistic guarantees on CFE robustness to model changes. This paper proposes a novel approach for generating CFEs that provides probabilistic guarantees for any model and change type, while offering interpretable and easy-to-select hyperparameters. We establish a theoretical framework for probabilistically defining robustness to model change and demonstrate how our BetaRCE method directly stems from it. BetaRCE is a post-hoc method applied alongside a chosen base CFE generation method to enhance the quality of the explanation beyond robustness. It facilitates a transition from the base explanation to a more robust one with user-adjusted probability bounds. Through experimental comparisons with baselines, we show that BetaRCE yields robust, most plausible, and closest to baseline counterfactual explanations.
@inproceedings{stepka2024cfeprob, title = {Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change}, author = {St\k{e}pka, Ignacy and Lango, Mateusz and Stefanowski, Jerzy}, booktitle = {31st SIGKDD Conference on Knowledge Discovery and Data Mining - Research Track}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, year = {2025}, doi = {10.1145/3690624.3709300} }