Spatio-Temporal-GNN
Spatial and temporal graph neural networks for semantic trajectories represented in knowledge graphs.
PHD RESEARCHER · STORIES TEAM, LIG
Learning from
graphs.
Connecting ideas.
I’m Ali Elrida Shahimi. I explore how graph neural networks and knowledge graphs can help us learn from data that evolves across space and time.
BASED INGrenoble, FranceRESEARCHINGSpatiotemporal AI
A new chapter · October 2026
Graph neural networks✳Knowledge graphs✳Semantic trajectories✳Symbolic + neural AI
01 / ABOUT ME
Structure, meaning,
and what comes next.
My research sits at the intersection of graph learning, semantic representations, and spatiotemporal data.
I started my PhD in October 2026 with the STORIES team at LIG in Grenoble, continuing the work I began during my master’s research internship on graph neural networks for spatiotemporal knowledge graphs.
I graduated with a master’s degree in Computer Engineering from Politecnico di Torino in July 2026, with a final grade of 107/110. My studies also took me to INP Grenoble for an M2 exchange, where I explored generative multimodal AI, GPU computing, and computer vision.
I’m particularly interested in bringing semantic structure and deep learning together: building representations that connect the relationships in our data with the ways they change over time.
LANGUAGESArabic NativeEnglish FluentItalian Basic
02 / THE JOURNEY
One path. New questions.
From computer engineering foundations
to research in graph learning.
- 2021 — 2024THE FOUNDATION
Bachelor’s in Computer Engineering
Politecnico di Torino
A foundation in computer engineering, leading into advanced study in artificial intelligence, machine learning, and software systems.
- 2024 — 2026FROM STUDY TO RESEARCH
Master’s in Computer Engineering
Politecnico di Torino · M2 exchange at INP Grenoble
Graduated in July 2026 with a final grade of 107/110. During my 2026 internship with the STORIES team at LIG, I studied graph neural networks for spatiotemporal knowledge graphs representing semantic trajectories.
My work included ontology-guided graph snapshots from RDF data, self-supervised representation learning, clustering, and entity alignment analysis.
- 2026 — present THE CURRENT CHAPTER
PhD · Continuing the research
STORIES team · Laboratoire d’Informatique de Grenoble (LIG)
Started in October 2026, extending the research initiated during my master’s internship. My focus brings graph neural networks and spatiotemporal knowledge graphs together, with an interest in hybrid symbolic-neural approaches.
03 / SELECTED WORK
Ideas in practice.
A selection from my project portfolio, spanning research, GPU computing, and software development.
GRAPH LEARNING
word2vec-cuda
A CUDA implementation of Word2Vec, exploring GPU programming and parallel computation.
DDPM / Diffusion modeling
An implementation study of denoising diffusion probabilistic models.
GeoControl
A team-based IoT monitoring system for real-time environmental data visualization.
Stuff-Happens
A full-stack web application built with React and Node.js.
04 / TOOLKIT
The tools
behind the work.
Also learning through
IBM · Generative AI Models for NLP & NLU
Verified certificate · edX · October 2025
Programming
Python · C · C++ · Java · JavaScript · TypeScript
Learning & computation
PyTorch · TensorFlow · NumPy · CUDA · OpenCV
Graphs & semantics
NetworkX · rdflib · RDF · OWL · SPARQL
Software & workflow
React · Node.js · HTML / CSS · SQLite · Git · Linux · Jupyter
05 / GET IN TOUCH
Good research starts
with a conversation.
For research discussions, collaborations, or a hello.