{"id":5598,"date":"2021-02-16T18:49:51","date_gmt":"2021-02-16T17:49:51","guid":{"rendered":"https:\/\/kinit.sk\/member\/branislav-pecher\/"},"modified":"2025-06-25T22:47:53","modified_gmt":"2025-06-25T20:47:53","slug":"branislav-pecher","status":"publish","type":"member","link":"https:\/\/kinit.sk\/sk\/clen\/branislav-pecher\/","title":{"rendered":"Branislav Pecher"},"content":{"rendered":"
\n

Branislav is a PhD student focusing on misinformation detection and related phenomena, as well as on learning models that involve only a limited number of annotated samples, particularly meta-learning. He is also interested in the interpretability and explainability of various machine learning models, especially neural networks. <\/p>\n<\/div>\n\n

\n

He holds a Masters\u2019 degree in Intelligent Software Systems from the Slovak University of Technology. During his studies, he received multiple Rector\u2019s awards for excellent study performance and graduated magna cum laude. He has participated in both national and international research projects and is a former member of a PeWe (Personalized Web) research group.<\/p>\n<\/div>\n\n

\n

PhD topic: Addressing effects of randomness on the stability of learning with limited labelled data<\/h3>\n<\/div>\n\n
\n

Supervising team:<\/strong> M\u00e1ria Bielikov\u00e1<\/a> (KInIT), Ivan Srba<\/a> (KInIT)<\/p>\n<\/div>\n\n

\n

Learning with limited labelled data, including but not limited to concepts such as zero\/few-shot learning, transfer learning or meta-learning, aims to effectively train a model while using only a small amount of labelled samples. Although such approaches were successfully applied in many domains, they are especially sensitive to the effects of uncontrolled randomness caused by non-determinism in the training process. The non-determinism negatively affects the stability of the trained models and leads to large variance in results across training runs. Such uncontrolled randomness can unintentionally, but unfortunately also intentionally, create an imaginary perception of research progress. When disregarded, the randomness can prohibit objective comparison of new methods, leading to overestimation, or in some cases underestimation, of their performance. Even though a growing number of studies focus on addressing the negative effects of randomness on stability, the research is still limited in its extent, facing many problems and inconsistencies. <\/p>\n<\/div>\n\n

\n

Our aim in this work is to deal with the drawbacks when addressing the effects of randomness in learning with limited labelled data. Based on a comprehensive survey, we identify the most significant open problems, specifically the focus on investigation only on a small fragment of randomness, disregard for the interactions between sources of randomness and an absence of effective mitigation strategies. As a part of preliminary experiments, we design a general methodology for investigating effects of randomness. We apply this investigation methodology to determine the importance of multiple sources of randomness in meta-learning and language model fine-tuning. The preliminary results revealed a significant impact of randomness originating from splitting of data and selecting what data is labelled, which are mostly ignored in current research.<\/p>\n<\/div>\n\n

\n
\n