Summary
Télécom Paris and Télécom SudParis (Institut Polytechnique de Paris) are inviting applications for a 3-year fully funded PhD position in Graph Signal Processing and Graph Machine Learning. The project, titled SIGMA, is funded by Hi! PARIS and focuses on developing scalable learning methods that jointly summarize graph topology and graph signals using higher-order structures.
Fully Funded PhD in Graph Machine Learning & GNNs (Paris) France
Designation
PhD Researcher / PhD Candidate
Key Details
| Parameter | Details |
| Project Title | Signal-aware Graph Summarization with GNN Guarantees (SIGMA) |
| Position Type | PhD Position / Doctorate |
| Funding Body | Hi! PARIS |
| Duration | 3 Years |
| Expected Start Date | December 2026 |
| Supervisors | Jhony H. Giraldo & Aref Einizade |
| Host Institutions | Télécom Paris & Télécom SudParis (Institut Polytechnique de Paris) |
| Research Groups | MM Team at LTCI & ARMEDIA Team at SAMOVAR |
| Application Deadline | Rolling basis (open until filled) |
Research Area
- Graph Signal Processing
- Graph Machine Learning
- Geometric Deep Learning
- Keywords: Graph summarization, graph signals, higher-order structures, graph neural networks (GNNs), scalable learning.
Location
- Institutions: Télécom Paris and Télécom SudParis (Members of Institut Polytechnique de Paris)
- Address/Region: Paris-Saclay cluster, outskirts of Paris (~45 minutes by train from central Paris), France.
Eligibility / Qualification
- Degree: Currently holding or finishing a Master’s degree (M2) in Engineering, Data Science, Computer Science, Applied Mathematics, Signal Processing, Statistics, or an equivalent field.
- Background: Strong background in signal processing and machine learning, with a genuine interest in working in graph signal processing and geometric deep learning.
- Programming Skills: Strong proficiency in Python, including experience with PyTorch.
- Mathematics: A strong requirement to understand the mathematical foundations behind graph signal processing and geometric deep learning.
- Soft Skills: Excellent written and verbal communication skills.
Job Description
Graph datasets in social networks, recommender systems, biological networks, and knowledge graphs often contain millions or billions of nodes and edges, posing significant challenges for storage, analysis, and training Graph Neural Networks (GNNs).
Existing methods typically address graph-signal sampling or graph coarsening separately. The SIGMA PhD project aims to:
- Jointly compress the graph structure and its associated signals while preserving critical information for reconstruction and downstream tasks.
- Utilize meaningful higher-order structures as summarization units to capture complex relationships beyond simple nodes or edges.
- Develop efficient algorithms to select these structures on large-scale graphs with theoretical performance guarantees.
How to Apply
Interested candidates should send their application directly via email to the scientific contacts:
- Jhony H. Giraldo:
jhony.giraldo@telecom-paris.fr - Aref Einizade:
aref.einizade@telecom-sudparis.eu
Required Application Documents:
- Full CV
- Motivation Letter explaining your interest in the position (maximum 1 page)
- Transcript of Records (academic grades)
- Recommendation Letter(s) (at least one)
Last Date for Apply
Open Now
