Hubert Baniecki

h.baniecki@uw.edu.pl

Luck is what happens when preparation meets opportunity.

I am a 1st year PhD student in Computer Science at the University of Warsaw advised by Przemysław 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 biomedicine, 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 Jan	A paper The Grammar of Interactive Explanatory Model Analysis is accepted for publication in Data Mining and Knowledge Discovery.
2022 Dec	A paper SurvSHAP(t): Time-dependent explanations of machine learning survival models is accepted for publication in Knowledge-Based Systems.
2022 Oct	A paper Multi-omics disease module detection with an explainable Greedy Decision Forest is published in Scientific Reports.
2022 Sep	I got admissioned to PhD in Computer Science at the University of Warsaw & with external funding from the National Science Centre (Poland) PRELUDIUM BIS research grant ARES: Attack-Resistant Explanations toward Secure and trustworthy AI. Thanks to my supervisor Przemysław Biecek.
2022 Sep	I graduated with an MSc in Data Science from Warsaw University of Technology by defending a thesis titled From manipulating to evaluating explanations of machine learning models.

selected publications [more]

DMKD special issue

The Grammar of Interactive Explanatory Model Analysis

H. Baniecki, D. Parzych, P. Biecek

Data Mining and Knowledge Discovery, 2023
Interactive sequential model analysis improves the performance of human decision making.

Abstract arXiv Website

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? It turns out that this is an ill-posed question. One cannot sufficiently explain a black-box machine learning model using a single method that gives only one perspective. Isolated explanations are prone to misunderstanding, leading to wrong or simplistic reasoning. This problem is known as the Rashomon effect and refers to diverse, even contradictory, interpretations of the same phenomenon. Surprisingly, most methods developed for explainable and responsible machine learning focus on a single-aspect of the model behavior. In contrast, we showcase the problem of explainability as an interactive and sequential analysis of a model. This paper proposes how different Explanatory Model Analysis (EMA) methods complement each other and discusses why it is essential to juxtapose them. The introduced process of Interactive EMA (IEMA) derives from the algorithmic side of explainable machine learning and aims to embrace ideas developed in cognitive sciences. We formalize the grammar of IEMA to describe potential human-model dialogues. It is implemented in a widely used human-centered open-source software framework that adopts interactivity, customizability and automation as its main traits. We conduct a user study to evaluate the usefulness of IEMA, which indicates that an interactive sequential analysis of a model increases the performance and confidence of human decision making.
ECML PKDD oral

Fooling Partial Dependence via Data Poisoning

H. Baniecki, W. Kretowicz, P. Biecek

In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2022
This work is the core of our BSc thesis defended at Warsaw University of Technology in 2021.

Abstract PDF arXiv Code

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 not robust nor trustworthy, and they can be fooled. This paper presents techniques for attacking Partial Dependence (plots, profiles, PDP), which are among the most popular methods of explaining any predictive model trained on tabular data. We showcase that PD can be manipulated in an adversarial manner, which is alarming, especially in financial or medical applications where auditability became a must-have trait supporting black-box models. The fooling is performed via poisoning the data to bend and shift explanations in the desired direction using genetic and gradient algorithms. To the best of our knowledge, this is the first work using a genetic algorithm for attacking explanations, which is highly transferable as it generalizes both ways: in a model-agnostic and an explanation-agnostic manner.
JMLR award

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
This work received the John M. Chambers Statistical Software Award by ASA in 2022.

Abstract HTML Code Website

In modern machine learning, we observe the phenomenon of opaqueness debt, which manifests itself by an increased risk of discrimination, lack of reproducibility, and deflated performance due to data drift. An increasing amount of available data and computing power results in the growing complexity of black-box predictive models. To manage these issues, good MLOps practice asks for better validation of model performance and fairness, higher explainability, and continuous monitoring. The necessity for deeper model transparency comes from both scientific and social domains and is also caused by emerging laws and regulations on artificial intelligence. To facilitate the responsible development of machine learning models, we introduce dalex, a Python package which implements a model-agnostic interface for interactive explainability and fairness. It adopts the design crafted through the development of various tools for explainable machine learning; thus, it aims at the unification of existing solutions. This library's source code and documentation are available under open license at https://python.drwhy.ai.