About

About the DMML group

The Data Mining and Machine Learning group of Geneva was established in 2011 by Prof. Alexandros Kalousis. It operates as a collaboration between the Department of Information Systems of the University of Applied Sciences, Western Switzerland, Geneva, and the VIPER group of the Computer Science Department of the University of Geneva. Many of the members currently follow a PhD under the joint supervision of Profs. Alexandros Kalousis and Stephane Marchand-Maillet.

We conduct research in various areas of data mining and machine learning, publishing at major international conferences (NeurIPS, ICML, etc.). In our latest work we focus on leveraging the power of modern deep learning architectures to address the problems of generative modeling, continual- and meta- learning, modelling of dynamical systems, and imitation and reinforcement learning. In these we also build on our experiences with metric and kernel learning, feature selection, structured regularization, and many other topics explored over the years by our members.

Many of our research directions have been defined on the basis of real world problems. We collaborate with multiple industrial and academic partners on joint projects providing the necessary machine learning expertise. The group receives funding from different sources, such as the Swiss National Science Foundation, SNSF, InnoSuisse (former CTI), the European Union, Horizon 2020, as well as directly from industrial partners.

News

Archive of news

  • 2020 Retrospective

    9.12.2020

    What a year this was...! This retrospective though, won't be about the unprecedented situation that we all went through. We'll take some time to revisit the highlights of our group's activities throughout this year. Let's go!

    Read more
  • PhD student position, University of Geneva (Comput…

    30.11.2020

    We have an opening for a PhD position. The research target is the development of deep generative models that can incorporate strong domain knowledge within the learning process. Such domain knowledge, typically available in scientific fields, can be encoded in various forms such as equation-based models (e.g. physics and chemistry), simulators (e.g. biomechanical models), and ...

    Read more
  • Papers in NeurIPS 2020

    9.10.2020

    We are very happy to announce that the members of our team have had two accepted papers in NeurIPS 2020!

    Read more