PhD Position in Compression and Efficient Processing of Graph Data: From Signal Processing to Deep Learning
We are opening a PhD position at Télécom Paris (Institut Polytechnique de Paris) within the Institut Mines-Télécom (IMT) Futur, Ruptures & Impacts 2026 program on the topic:
Compression and Efficient Processing of Graph Data: From Signal Processing to Deep Learning
This PhD lies at the intersection of graph signal processing, graph machine learning, and geometric deep learning. The goal is to develop principled graph and signal compression methods with theoretical recovery and downstream learning guarantees, enabling efficient and trustworthy learning on large-scale graph data.
The project combines solid mathematical foundations (sampling, reconstruction, spectral theory) with modern GNNs and higher-order graph learning.
Supervisors:
- Jhony H. Giraldo (Télécom Paris)
- Aref EINIZADE (Télécom SudParis)
- Antonio Ortega (University of Southern California)
We are looking for candidates who:
- Hold (or are completing) an M2 or final-year engineering degree in applied mathematics, signal processing, computer science, or related fields
- Have strong foundations in signal processing and machine learning
- Are comfortable with Python / PyTorch
- Have a strong interest in theory-driven research in graph signal processing and geometric deep learning
Practical information:
- Location: Télécom Paris, Palaiseau
- Start date: September / October 2026
- Duration: 3 years
Applications must be submitted via the official IMT PhD platform: https://phd.imt.fr/en/formation/data-analytics-artificial-intelligence/1766421231-31-compressing-graph-data-signal
Deadline: February 15, 2026
Full PhD description: https://docs.google.com/viewer?url=raw.githubusercontent.com/jhonygiraldo/jhonygiraldo.github.io/master/assets/pdf/PhD_Position.pdf
Incomplete applications won't be considered.