CHAI Seminar: Research Talk, Bartosz Krawczyk, Assistant Professor of Machine Learning and Computer Vision (MLVision) Lab
CHAI Seminar Series
Refreshments will be served
DATE: October 20, 12:00-1:00 PM
SPEAKER: Bartosz Krawczyk, Assistant Professor of Machine Learning and Computer Vision (MLVision) Lab.
IN-PERSON: GOL CYB-1710-1720
TITLE: Learning under Data Difficulties: Class Imbalance, Fairness, and the Next Frontier of Robust AI
ABSTRACT: Modern machine learning systems are often deployed in environments where data is far from balanced. In practice, a few classes dominate, while rare or minority categories — often those most critical for decision-making — are underrepresented. This long-tailed distribution not only challenges recognition accuracy but also raises profound questions of fairness, equity, and trustworthiness in AI. Over the past decade, research on class imbalance and long-tailed learning has progressed from algorithmic adjustments to more principled approaches that balance representation, optimize loss landscapes, and integrate domain priors. In this talk, I will highlight recent advances and open challenges in long-tailed recognition and fairness-aware learning, drawing connections to real-world applications, where minority performance matters most. I will also outline how imbalance and fairness intersect with continual learning, where evolving data streams exacerbate hidden biases and create new forms of imbalance over time. By unifying perspectives from imbalance handling, fairness, and continual adaptation, we can move towards robust and responsible AI systems that perform well not only in the majority but also where data is scarce, evolving, or structurally disadvantaged.
BIO: Bartosz Krawczyk is an assistant professor in the Chester F. Carlson Center for Imaging Science at the Rochester Institute of Technology, where he heads MLVision Lab. Dr. Krawczyk's current research interests include machine learning, continual and lifelong learning, data streams and concept drift, class imbalance, and explainable artificial intelligence. He has authored more than 70 journal papers and over 100 contributions to conferences. Dr. Krawczyk coauthored the book Learning from Imbalanced Data Sets (Springer 2018). He was a recipient of several awards for his scientific achievements, such as the IEEE Richard Merwin Scholarship, IEEE Outstanding Leadership Award, Amazon Machine Learning Award and Best Paper Award at CLVISION CVPR.
Event Snapshot
When and Where
Who
Open to the Public
Interpreter Requested?
No