MSCA Postdoctoral Fellow 2024 Host on Graph Neural Networks (GNNs)

Nisrine JRAD from the Université catholique de l'Ouest (UCO) in Angers, France, is seeking a postdoctoral fellow to submit a MSCA PF 2024 project on Graph Neural Networks (GNNs) for node classification tasks.

About LARIS Laboratory

LARIS is a multidisciplinary research unit in Science and Technology belonging to the University of Angers (UA) which research thematics are :

• The study of dynamic systems, particularly discrete-event systems, and their optimization;
• Signal and image processing, applied to life sciences;
• Reliability and operational performances of complex system.

The postdoctoral fellow will be working with "Information, Signal, Image and Life Sciences (ISISV)" group of the LARIS. ISISV is interested in information processing at the interface with physics, as well as in signal and image processing applied to the life sciences (medical and plant applications).

The contributions of the team are both methodological, technological and clinical and the finalities are interpretation and decision support. In particular for the medical aspects, the applied objective concerns the diagnosis of pathologies and a better understanding of medical data in cardiovascular and neurology.

About the Université catholique de l’Ouest (UCO)

Founded in 1875, UCO is one of the oldest universities in Western France, and a key player in today's higher education and research landscape. A multi-disciplinary and multi-campus university, it is home to some 12,800 students and over 200 researchers in 12 teams across 6 faculties. Researchers at UCO work in close collaboration with researchers at several universities in France (e.g. Nantes, Angers, Rennes, Lorient, Strasbourg) and abroad. They carry out research in a wide variety of disciplines and participate in national and international projects. Each year, UCO also welcomes several doctoral students and offers post-doctoral contracts, providing young researchers with training through research.

Presentation of the project

Title: Graph Neural Networks (GNNs) for node classification tasks

In the last decade, Deep Learning, particularly Convolutional Neural Networks (CNNs), has significantly influenced several machine learning applications, including image recognition and signal processing. These accomplishments have primarily involved sequences (1D) or images (2D) data structured on grid formats that leverage linear algebra operations in Euclidean spaces. However, numerous domains, such as social networks, traffic networks, brain networks, molecules, and knowledge graphs, pose challenges as their data cannot be straightforwardly encoded into Euclidean domain but lends itself to natural representation as graphs.

Graphs serve as a robust tool for representing data generated by both artificial and natural processes. They possess a dual nature, being composed of atomic information pieces or entities (known as nodes) while exhibiting relational structures defined by links among entities (edges). The omnipresence of graphs is noteworthy. In social sciences, graphs are used for depicting interpersonal relationships, in recommending systems they model intricate purchasing patterns. In social networks they are used to identify communities, and in traffic networks, they can predict traffic and optimise routing.

The increasing wealth of graph data, along with the expanding accessibility of extensive repositories, has encouraged researchers to extend the deep learning paradigm to graph world. The objective of our work is to revisit Neural Networks to operate on graph data, to benefit from the representation learning ability. In this context, many Graph Neural Networks (GNNs) have been recently proposed in the literature of geometric learning. The goal of this project is to introduce innovative Graph Neural Network (GNN) algorithms for node classification. The primary objectives encompass both fundamental and practical aspects, with a potential focus on applications related to epilepsy.

Keywords : Graph Neural Networks (GNNs), Nodes classification, Artificial Intelligence, Machine Learning, Deep Learning

Eligibility

Applicants must comply with the mobility rule (having stay in France less than 12 months in the past 3 years before the 11th of September 2024). Applicants also must have maximum 8 years of research experience after graduating their (first) PhD.

If you are interested in this offer and have the required background, please apply by sending your CV and the application form (available here) to: njrad@uco.frand cap-europe@univ-angers.fr

As part of the application, there is a possibility to fund the mobility of the fellow selected to Angers to work during 2-3 days with the supervisor on the proposal before mid-july 2024. For further information, please contact : cap-europe@univ-angers.fr

We encourage you to apply ASAP, if we receive application that has a fitting profile, we will close the offer in Euraxess.