HYBRID EVENT: You can participate in person at London, UK or Virtually from your home or work.

5th Edition of Euro-Global Conference on Biotechnology and Bioengineering

September 18-20 | Hybrid Event

September 18-20, 2025 | London, UK
ECBB 2025

Information Leakage: Types, remedies, and open problems

Julia Sidorova, Speaker at Bioengineering Conferences
Centro de Investigación Biomédica En Red Enfermedades Hepáticas y Digestivas (CIBEREHD), Spain
Title: Information Leakage: Types, remedies, and open problems

Abstract:

Information Leakage threatens and questions the use of machine learning model in real-life clinical applications. In effect, information leakage is similar to vulgar overfitting, yet rather more subtle and even when detected much harder to remove. Some recent research indicates that if overfitting is removed, deep neural networks perform systematically worse than linear regression models. This statement is not very far from our results in survival analysis. There are different types of leakage and some are specific to deep neural netowrks,e.g. the effects of pretraining have not been thoughreghly studied. In the talk, I will review the current understanding of what is information leakage and its subtypes. The types and examples were largely defined within different applications of machine learning. The RQ asked is: -- Is there anything a clincial bioinformatician should learn from the current concerns and work done in chemoinformatics, political science etc. Do the protocols of analysis keep us safe and where it is dangerous waters?

Biography:

Born in 1980, PhD from Universidad Pompeu Fabra in 2009, Spain. After an extensive and international postdoctoral training in algorithms and bioinformatics (incl. Universidad Carlos III de Madrid, ETH-Zurich), she served as an Assistant Professor at Blekinge Institute of Technology, Sweden, where she was predominantly working in industrial projects with Sony, Boeing, Telenor, Ericsson. In 2019/2020 she held a position of honour at Universidad Complutense de Madrid and was an Adjunct Professor teaching research methodology and deep learning at KTH Royal Institute of Technology, Stockholm. From 2021, she is a Senior Researcher in service at the CIBER, the Spanish national consortium of hospitals. As far as research is concerned, her interests lie in classical data analysis vs deep neural networks, -- understanding their suitability or deficiencies. She serve at the Editorial Board of Frontiers of Neuroscience (Biomakers).

Watsapp
a