Guillaume
Salha-Galvan

Guillaume SALHA-GALVAN

Machine Learning Researcher

GitHub - LinkedIn - Bluesky

gsalhagalvan [at] gmail [dot] com





Hosted on GitHub Pages — Theme by orderedlist

Bio

I am a French researcher specializing in Graph-Based Machine Learning and Recommender Systems, with a Ph.D. from École Polytechnique and over seven years of experience in the music tech industry.

Until recently, I was a Research Scientist and Coordinator on Music Recommendation at Deezer. From 2018 to 2024, I conducted research on Machine/Deep Learning, Graph Representation Learning, Information Retrieval, and Recommender Systems as part of the Research team in France. Previously, from 2016 to 2018, I worked as a Data Scientist in the company, collaborating with cross-functional teams to enhance the user experience.

My research has resulted in over 30 scientific publications in peer-reviewed journals and international conferences, earning best paper awards or honorable mentions at RecSys 2020, 2021, and 2024, as well as at ECIR 2024. Several of these publications describe algorithms now powering Deezer's recommender systems, helping millions of users worldwide discover new music daily.

I completed my Ph.D. from 2018 to 2022 alongside my work at Deezer, through a scientific partnership with École Polytechnique. I was supervised by Romain Hennequin and Michalis Vazirgiannis. Prior to that, I graduated in 2016 from ENS Paris-Saclay with an M.Sc. in Machine Learning (MVA), and from ENSAE Paris with an M.Eng. in Data Science, both with first-class honours.

I am now embarking on the next chapter of my career and look forward to sharing more soon!



News



Publications

See me also on Google Scholar and ORCID.org.

2025

2024

Note: publications from 2023 and 2024 reflect my Research Coordinator role at Deezer, where I was responsible for supervising projects. I am often listed as the second or last author in these articles.

2023

2022

2021

2020

Note: I published under the name G. Salha until 2020.

2019

2018