法国国家信息与自动化研究所2020年博士后职位招聘

2020-02832 - Post-Doctoral Research Visit F/M Invariant graph representation learning for volumetric data processing

Contract type : Fixed-term contract

Level of qualifications required : PhD or equivalent

Fonction : Post-Doctoral Research Visit

About the research centre or Inria department

The Inria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has more than thirty research teams. The Inria Center is a major and recognized player in the field of digital sciences. It is at the heart of a rich R&D and innovation ecosystem: highly innovative PMEs, large industrial groups, competitiveness clusters, research and higher education players, laboratories of excellence, technological research institute, etc.

Assignment

The recruited person will be in connection with the LTS4 (EPFL, Switzerland) in the context of the International Labs EPFL-Inria

Main activities

In this postdoctoral project, we will propose new graph representation learning techniques. More precisely, we will be given some visual data defined on graph structures, driven by the underlying geometry of the scene and the capture system. In most of the existing scheme, this kind of data are first mapped to euclidean space before processing, loosing the specific topology captured by the graph. Our aim will be to learn a low-dimensional representation of the graph and the signal so that analysis and compression can be more effective.

1D. I. Shuman, S. K. Narang, P. Frossard, A. Ortega, and P. Vandergheynst, “The emerging fieldof signal processing on graphs: Extending high-dimensional data analysis to networks and otherirregular domains,”IEEE signal processing magazine, vol. 30, no. 3, pp. 83–98, 2013.

2F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini, “The graph neuralnetwork model,”IEEE Transactions on Neural Networks, vol. 20, no. 1, pp. 61–80, 2008.

3M. M. Bronstein, J. Bruna, Y. LeCun, A. Szlam, and P. Vandergheynst, “Geometric deeplearning: going beyond euclidean data,”IEEE Signal Processing Magazine, vol. 34, no. 4, pp.18–42, 2017.

4W. L. Hamilton, R. Ying, and J. Leskovec, “Representation learning on graphs: Methods andapplications,”arXiv preprint arXiv:1709.05584, 2017.

5P. W. Battaglia, J. B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski,A. Tacchetti, D. Raposo, A. Santoro, R. Faulkneret al., “Relational inductive biases, deeplearning, and graph networks,”arXiv preprint arXiv:1806.01261, 2018.

6P. Goyal and E. Ferrara, “Graph embedding techniques, applications, and performance: Asurvey,”Knowledge-Based Systems, vol. 151, pp. 78–94, 2018

Skills

Technical skills and level required :

Languages :

Relational skills :

Other valued appreciated :

Benefits package

 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)

 Professional equipment available (videoconferencing, loan of computer equipment, etc.)

 Social, cultural and sports events and activities

 Access to vocational training

 Social security coverageRemuneration

Monthly gross salary amounting to 2653 euros

General Information

Theme/Domain : Vision, perception and multimedia interpretation Statistics (Big data) (BAP E)

Town/city : Rennes

Inria Center : CRI Rennes - Bretagne Atlantique

Starting date : 2020-11-01

Duration of contract : 2 years

Deadline to apply : 2020-08-31Contacts

Inria Team : SIROCCO

Recruiter : Maugey Thomas / thomas.maugey@inria.fr