I am a Research Scientist at Deezer, a global music streaming platform, in Paris, France. Since October 2018, I am simultaneously pursuing a Ph.D. in Machine Learning at École Polytechnique, under the supervision of Romain Hennequin and Michalis Vazirgiannis.
My research interests span the broad areas of Deep Learning and Graph Mining, with application to Music Representation and Recommendation. In my recent publications, I mainly focused on Graph Representation Learning and notably on Graph Autoencoders.
Prior to my Ph.D., I worked as a Data Scientist at Deezer for two years, conducting product-oriented projects to improve UX, conversion and churn. Even before, I also handled exciting challenges in Canada and in China. Feel free to visit my LinkedIn profile for more details about my experience.
I graduated in 2016 from École Normale Supérieure Paris-Saclay, completing a Master's degree (M.Sc.) in Computer Vision and Machine Learning (MVA), and from ENSAE Paris, completing a Master of Engineering (M.Eng.) in Data Science, both with first class honours.
Sept. 2020: Our work on music genre perception has been accepted at EMNLP!
Feb. 2020: Deezer Research has a brand new website!
FastGAE: Scalable Graph Autoencoders with Stochastic Subgraph Decoding
, R. Hennequin, J.B. Remy, M. Moussallam, M. Vazirgiannis
Neural Networks 142, 1-19, Elsevier (Impact Factor: 5.53) [code]
Modeling the Music Genre Perception across Language-Bound Cultures
E.V. Epure, , M. Moussallam, R. Hennequin
Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), Virtual. [code] [data]
Carousel Personalization in Music Streaming Apps with Contextual Bandits
W. Bendada, , T. Bontempelli
ACM Conference on Recommender Systems (RecSys 2020), Virtual. [code] [data]
Best Short Paper Candidate
Simple and Effective Graph Autoencoders with One-Hop Linear Models
, R. Hennequin, M. Vazirgiannis
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2020), Virtual. [code]
Multilingual Music Genre Embeddings for Effective Cross-Lingual Music Item Annotation
E.V. Epure, , R. Hennequin
International Society for Music Information Retrieval Conference (ISMIR 2020), Virtual. [code] [data]
Muzeeglot : Annotation Multilingue et Multi-Sources d’Entités Musicales à partir de Représentations de Genres Musicaux
E.V. Epure, , F. Voituret, M. Baranes, R. Hennequin
27ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2020), Nancy, France. [code]
Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
, R. Hennequin, M. Vazirgiannis
Graph Representation Learning Workshop, Conference on Neural Information Processing Systems (NeurIPS GRL 2019), Vancouver, Canada. [code]
Gravity-Inspired Graph Autoencoders for Directed Link Prediction
, S. Limnios, R. Hennequin, V.A. Tran, M. Vazirgiannis
ACM International Conference on Information and Knowledge Management (CIKM 2019), Beijing, China. [code]
A Degeneracy Framework for Scalable Graph Autoencoders
, R. Hennequin, V.A. Tran, M. Vazirgiannis
International Joint Conference on Artificial Intelligence (IJCAI 2019), Macao, China. [code]