Hubert Baniecki

University of WarsawWarsaw University of TechnologyMI².AI

h.baniecki (at) uw.edu.pl

Luck is what happens when preparation meets opportunity.

I am a 2nd year PhD student in Computer Science at the University of Warsaw advised by Przemyslaw Biecek. Prior, I did my MSc (2022) and BSc (2021) in Data Science at Warsaw University of Technology, Poland.

My main research interest is explainable machine learning, with particular emphasis on adversarial attacks & explanation evaluation. I also care about human-model interaction with applications in medicine, and support the development of several open-source Python & R packages for building predictive models responsibly.

I received the 2022 John M. Chambers Statistical Software Award.


recent news [archive]

2023 Nov A paper survex: an R package for explaining machine learning survival models is accepted for publication in Bioinformatics.
2023 Jun A paper Adversarial Attacks and Defenses in Explainable Artificial Intelligence: A Survey is accepted for presentation at the IJCAI 2023 Workshop on XAI.
2023 Apr We are organising Joint workshops on XAI methods, challenges and applications (XAI^3) at the ECAI 2023 conference in Cracow, Poland. Paper submission deadline is July 18, 2023.
2023 Apr A paper Towards Evaluating Explanations of Vision Transformers for Medical Imaging is accepted for publication at CVPR 2023 Workshops.
2023 Mar A paper Hospital Length of Stay Prediction Based on Multi-modal Data Towards Trustworthy Human-AI Collaboration in Radiomics is accepted for publication at the AIME 2023 conference.

selected publications [more]

    1. The grammar of interactive explanatory model analysis
      H. Baniecki, D. Parzych, P. Biecek
      Data Mining and Knowledge Discovery, 2023
      Interactive analysis of a model improves the performance of human decision making.
    2. Fooling Partial Dependence via Data Poisoning
      H. Baniecki, W. Kretowicz, P. Biecek
      ECML PKDD 2022
      Feature effect explanations can be manipulated in an adversarial manner.
    3. dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python
      H. Baniecki, W. Kretowicz, P. Piatyszek, J. Wisniewski, P. Biecek
      Journal of Machine Learning Research, 2021
      For this work, I received the 2022 John M. Chambers Statistical Software Award.