Kalina Jasinska-Kobus
PhD

Contact Information:

kjasinska cs put poznan pl


I defended my PhD dissertation at the Laboratory of Intelligent Decision Support Systems in the Institute of Computing Science, Poznan University of Technology, Poland, under the supervision of Krzysztof Dembczynski. My current research interests include training robust classifiers under various types of noise, especially instance-dependent class noise, and metric learning in various applications.


Publications

  • Propensity-scored Probabilistic Label Trees
    Marek Wydmuch, Kalina Jasinska-Kobus, Rohit Babbar, Krzysztof Dembczynski
    Accepted to SIGIR (Short Papers Track), 2021
  • Online probabilistic label trees
    Marek Wydmuch, Kalina Jasinska-Kobus, Devanathan Thiruvenkatachari, Krzysztof Dembczynski
    PMLR, Volume 130: International Conference on Artificial Intelligence and Statistics, AISTATS, 2021
  • Probabilistic Label Trees for Extreme Multi-label Classification
    Kalina Jasinska-Kobus, Marek Wydmuch, Krzysztof Dembczyński
    Submitted to JMLR, 2020
    You can find the code in the GitHub repository: https://github.com/mwydmuch/napkinXC
  • BERT-based similarity learning for product matching
    Janusz Tracz, Piotr Wojcik, Kalina Jasinska-Kobus, Riccardo Belluzzo, Robert Mroczkowski, Ireneusz Gawlik
    Proceedings of the Workshop on Natural Language Processing in E-Commerce (EComNLP), 2020
  • Online probabilistic label trees
    Kalina Jasinska-Kobus, Marek Wydmuch, Devanathan Thiruvenkatachari, Krzysztof Dembczynski
    Extreme Classification Workshop at ICML, 2020
  • On the computational complexity of the probabilistic label tree algorithms
    Robert Busa-Fekete, Krzysztof Dembczyński, Alexander Golovnev, Kalina Jasinska, Mikhail Kuznetsov, Maxim Sviridenko, Chao Xu
    arxiv, 2019
  • A no-regret generalization of hierarchical softmax to extreme multi-label classification
    Marek Wydmuch, Kalina Jasinska, Mikhail Kuznetsov, Robert Busa-Fekete, Krzysztof Dembczyński
    Neural Information Processing Systems, 2018
    You can find the code in the GitHub repository: https://github.com/mwydmuch/extremeText
  • Extreme F-measure Maximization using Sparse Probability Estimates
    Kalina Jasinska, Krzysztof Dembczynski, Robert Busa-Fekete, Karlson Pfannschmidt, Timo Klerx, Eyke Hullermeier
    Proceedings of The 33rd International Conference on Machine Learning, 2016
    You can find the code in the GitHub repository: https://github.com/busarobi/XMLC

  • Log-time and Log-space Extreme Classification
    Kalina Jasinska, Nikos Karampatziakis
    The NIPS Workshop on Multi-class and Multi-label Learning in Extremely Large Label Spaces, 2016
    You can find the code in the GitHub repository: https://github.com/kjasinska/ltls
  • Extreme classification under limited space and time budget
    Kalina Jasinska, Krzysztof Dembczynski, Nikos Karampatziakis
    Schedae Informaticae - Theoretical Foundations of Machine Learning Conference, Krakow, 2016
  • Efficient exact batch prediction for label trees
    Kalina Jasinska
    Extreme Multilabel Classification for Social Media at The Web Conference, Lyon 2018
  • Bayes optimal prediction for NDCG@k in extreme multi-label classification
    Kalina Jasinska, Krzysztof Dembczynski
    DA2PL From Multiple Criteria Decision Aid to Preference Learning Workshop , Poznan, 2018
  • Consistent Label Tree Classifiers for Extreme Multi-Label Classification
    Kalina Jasinska, Krzysztof Dembczynski
    Extreme Classification Workshop 2015 at ICML, 2015

Profiles:

  • Google Scholar
  • Linkedin