2022-04542 - PhD Position F/M Privacy-Preserving Federated Machine Learning
Le descriptif de l’offre ci-dessous est en Anglais

Type de contrat : CDD

Niveau de diplôme exigé : Bac + 5 ou équivalent

Fonction : Doctorant

A propos du centre ou de la direction fonctionnelle

The Inria Lille - Nord Europe Research Centre was founded in 2008 and employs a staff of 360, including 300 scientists working in 15 research teams. Recognised for its outstanding contribution to the socio-economic development of the Hauts-De-France région, the Inria Lille - Nord Europe Research Centre undertakes research in the field of computer science in collaboration with a range of academic, institutional and industrial partners.

 The strategy of the Centre is to develop an internationally renowned centre of excellence with a significant impact on the City of Lille and its surrounding area. It works to achieve this by pursuing a range of ambitious research projects in such fields of computer science as the intelligence of data and adaptive software systems. Building on the synergies between research and industry, Inria is a major contributor to skills and technology transfer in the field of computer science.

Contexte et atouts du poste

The PhD student will be supervised by Aurélien Bellet, an Inria researcher in the Magnet project-team. Magnet (https://team.inria.fr/magnet/) is a research team that carries out research in Machine Learning in Information Networks, with an important focus on Natural Language Processing, Machine Learning under Privacy and Fairness Constraints, and Decentralized/Federated Learning. More specifically, the PhD will be part of the research project PRIDE (https://project.inria.fr/pride/) funded by the French National Research Agency (ANR).

This PhD will stimulate existing and emerging collaborations with other research groups on themes in the intersection between machine learning, decentralized algorithms and privacy. For instance, Magnet has ongoing collaborations with groups at EPFL (Switzerland), the privacy-preserving data analysis group at Alan Turing Institute (London, UK), as well as federated learning and privacy researchers at Google Research. The candidate will have the opportunity to spend some time abroad in these renowned teams.

In terms of concrete applications, Magnet recently started collaborations with Lille University Hospital (CHU) on decentralized machine learning through some joint projects. These collaborations will provide concrete use-cases to which the approaches developed in this thesis could be applied, for instance to run multi-centric decentralized medical studies while preserving the confidentiality of the datasets held in each institution.

Mission confiée

The successful candidate will conduct research in the area of decentralized (federated) and privacy-preserving machine learning. The precise topic of the PhD, and balance between theory and applications, is flexible and can (to some extent) be adapted to the candidate's preferences and skills.

Questions of particular interest include (but are not limited to):

  • Optimization algorithms for decentralized/federated machine learning
  • Differential privacy approaches for decentralized/federated machine learning
  • Secure computation for decentralized/federated machine learning
  • Applications to the medical domain

Principales activités

  1. Review and follow the existing literature on decentralized and federated algorithms
  2. Propose new algorithms and prove theoretical guarantees (on convergence/privacy/security...)
  3. Numerically evaluate the performance of the proposed approaches, possibly on real use-cases
  4. Publish and present results in top machine learning conferences and journals


A good candidate will have the following skills:

  • A good command of English
  • A strong background in computer science and/or mathematics
  • A good knowledge of machine learning, statistics and/or security
  • Preferably some knowledge on distributed systems
  • Some experience with implementation and experimentation
  • A broad interest for the topic of privacy is a plus

Please follow the instructions given in https://team.inria.fr/magnet/how-to-apply/ to set up your application file.


  • Subsidized meals
  • Partial reimbursement of public transport costs
  • Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
  • Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
  • Professional equipment available (videoconferencing, loan of computer equipment, etc.)
  • Social, cultural and sports events and activities
  • Access to vocational training
  • Social security coverage


1st and 2nd year : 1 982€ Gross monthly salary (before taxes) 

3rd year : 2085€ gross monthly salary (before taxes)