prof_pic.jpg

Vasilis Gkolemis


I am a 2nd year PhD candidate (2022-) in Explainable AI under the supervision of Prof. Christos Diou, Prof. Eirini Ntoutsi and Theodore Dalamagas. At the same time, I work as a Research Associate at ATHENA RC. Prior, I completed my MSc at the University of Edinburgh (2019-2021) and obtained 5-year Diploma from Aristotle University of Thessaloniki (2011-2017).


I do research in Explainable AI I and in particular on creating (a) novel explainable-by-design models and/or (b) novel explainability techniques for black-box models. I also have a special interest for probalistic models, where I explore and explain sources of the uncertainty.


Beyond my research background, I often work in captivating industrial projects, where I deliver Deep Learning solutions for addressing challenges in NLP and Computer Vision problems. Finally, I actively contribute to some open-source projects, like ELFI.


❢ For a more detailed view of my skillset, take a look at my CV.


Selected publications

  1. DALE
    DALE: Differential Accumulated Local Effects for efficient and accurate global explanations
    Vasilis Gkolemis, Theodore Dalamagas, and Christos Diou
    In Asian Conference on Machine Learning (ACML) Oct 2022
  2. RAM
    Regionally Additive Models: Explainable-by-design models minimizing feature interactions
    Vasilis Gkolemis, Anargiros Tzerefos, Theodore Dalamagas, and 2 more authors
    In Accepted at European Conference in Machine Learning (ECML) Sep 2023
  3. RHALE
    RHALE: Robust and Heterogeneity-aware Accumulated Local Effects
    Vasilis Gkolemis, Theodore Dalamagas, Eirini Ntoutsi, and 1 more author
    Oct 2023
  4. ROMC
    An Extendable Python Implementation of ROMC
    Vasilis Gkolemis, Michael Gutmann, and Henri Pesonen
    In Accepted at Journal of Statistical Software (JSS) Sep 2023

Selected talks

  1. BayesianInference
    Bayesian Inference and ROMC
    V. Gkolemis
    Nov 2021
  2. GlobalXAI
    Overview of Global Explainability Methods
    V. Gkolemis
    Mar 2023