Research themes

Our research is interdisciplinary focusing on data-driven analysis of evolutionary processes in nature and society.

Our group hosts computer scientists, geoscientists, a mathematician, a physicist. We work with many interdisciplinary collaborators.

Our main funded projects currently focus on global scale analysis of biospheric change, evolutionary processes, reconstructing past climates and environmental change. In data science our primary focus is on methods for handling concept drift, and reasoning with evolving data. We are also concerned how to make robust, transparent and interpretable models in general.
Data science and evolution

Data science for understanding evolutionary processes and how life works in general using data of the global fossil record, present day animal communities, climate, vegetation and environemnt models and sensory observations. Research directions include analysis of macroevolutionary processes, large scale reconstruction of paleoclimate, understanding evolution of faunal communities and contexts of human evolution, and providing quantitative insights for mitigating climate change.

Keywords: Red Queen, ecometrics, macroevolution, biospheric change and conservation palaeobiology, human environments

Key publications

  • by by Žliobaitė et al. 2017 in Nature.
  •  by Žliobaitė et al. 2016 in PNAS.
  • by Žliobaitė 2019 in Data Mining and Knowledge Discovery.
  • by Žliobaitė and Fortelius 2018 in Journal of Biomechanics.

Press coverage

  • Science News Daily - 
  • New Scientist - 
  • Yliopisto-lehti - 
  • International Business Times - 
Machine learning for evolving data

Our long tern focus in computational research has been on handling concept drift in machine learning. Traditional machine learning and data mining methods rely on the assumption that data distribution stays the same during model training and operation. As the world is continuously changing, so evolve data that describe it. We develop machine learning methods that can diagnose themselves and adapt to changing data distribution over time.

Keywords: concept drift, change detection, evolving streaming data

Key publications 

  •  by Gama et al. 2014 in ACM Computing Surveys.
  •  by Žliobaitė and Gabrys 2014 in IEEE Transactions on Knowledge and Data Engineering.
  •  by Žliobaitė et el. 2014 in IEEE Transactions on Neural Networks and Learning Systems.
  •  by Žliobaitė et al. 2015 in Machine Learning.
  •  by Žliobaitė and Hollmén 2015 in Machine Learning.
  •  by Žliobaitė et al. 2015 in Neurocomputing.
Data science in various domains

Applied data science is about translating human expertise from various domains to computational proxies and then modeling human expertise in a data-driven way. We have worked in data science in various domains, including: palaeobiology, forestry, biomedicine, chemical engineering, hardware design, traffic and mobility analysis, finance, process mining, sales analysis and customer profiling.

Selected publications: 

  •  by Žliobaitė et al. 2014 in SIGMOD Record.

  •  by Žliobaitė et al. 2014 in Atmospheric Measurement Techniques.

  •  by Martin-Salvador et al. 2014 in Procedia Computer Science.

  •  by Krilavičius et al. 2016 in IEEE CBMS.

  • by Kulmala et al. 2016 in Silva Fennica.

  •  by Žliobaitė et al. 2016 in PNAS.
Transparency and accountability in data science

Fairness-aware machine learning studies in which circumstances algorithms may become biased towards or against groups of people, and how to make predictive models free from such biases, when data, on which they are built, may be biased, incomplete, or even contain past discriminatory decisions. 

Selected publications:

  •  by Žliobaitė et al. 2011 in IEEE ICDM.
  •  by Calders and Žliobaitė 2013, a book chapter.
  •  by Žliobaitė 2015 in FATML workshop.
  •  by Žliobaitė and Custers 2016 in Artificial Intelligence and Law.
  •  by Žliobaitė 2017 in Data Mining and Knowledge Discovery.
  •  by Žliobaitė 2017 in Arxiv