Rate My Professor Celine Vens

Her research centers on developing machine learning algorithms for biomedicine and healthcare applications, including predictive models for clinical decision support, multi-output learning such as multi-label, multi-target, and hierarchical prediction, tree-based ensemble learning, explainable models, survival analysis, interaction prediction, and recommender systems. Key publications include "Decision Trees for Hierarchical Multi-label Classification" (Machine Learning, 2008), "Predicting Human Olfactory Perception from Chemical Features of Odor Molecules" (Science, 2017), "Tree Ensembles for Predicting Structured Outputs" (Pattern Recognition, 2013), "Predicting Gene Function Using Hierarchical Multi-label Decision Tree Ensembles" (BMC Bioinformatics, 2010), and "Drug-target Interaction Prediction with Tree-ensemble Learning and Output Space Reconstruction" (BMC Bioinformatics, 2020). She holds editorial roles as Action Editor for Machine Learning journal and board member for Data Mining and Knowledge Discovery and Artificial Intelligence in Medicine journals. Vens co-chaired the ECML-PKDD 2017 conference, chaired Benelearn 2016, and participates in program committees of international conferences. Her team achieved first place in the 2024 DREAM Olfactory Mixtures Prediction Challenge and secured FWO projects and mandates.