Alert button
Picture for Thomas Bouabça

Thomas Bouabça

Alert button

On the Consistency of Average Embeddings for Item Recommendation

Aug 30, 2023
Walid Bendada, Guillaume Salha-Galvan, Romain Hennequin, Thomas Bouabça, Tristan Cazenave

Figure 1 for On the Consistency of Average Embeddings for Item Recommendation
Figure 2 for On the Consistency of Average Embeddings for Item Recommendation
Figure 3 for On the Consistency of Average Embeddings for Item Recommendation
Figure 4 for On the Consistency of Average Embeddings for Item Recommendation

A prevalent practice in recommender systems consists in averaging item embeddings to represent users or higher-level concepts in the same embedding space. This paper investigates the relevance of such a practice. For this purpose, we propose an expected precision score, designed to measure the consistency of an average embedding relative to the items used for its construction. We subsequently analyze the mathematical expression of this score in a theoretical setting with specific assumptions, as well as its empirical behavior on real-world data from music streaming services. Our results emphasize that real-world averages are less consistent for recommendation, which paves the way for future research to better align real-world embeddings with assumptions from our theoretical setting.

* 17th ACM Conference on Recommender Systems (RecSys 2023) 
Viaarxiv icon

Track Mix Generation on Music Streaming Services using Transformers

Jul 06, 2023
Walid Bendada, Théo Bontempelli, Mathieu Morlon, Benjamin Chapus, Thibault Cador, Thomas Bouabça, Guillaume Salha-Galvan

Figure 1 for Track Mix Generation on Music Streaming Services using Transformers
Figure 2 for Track Mix Generation on Music Streaming Services using Transformers
Figure 3 for Track Mix Generation on Music Streaming Services using Transformers

This paper introduces Track Mix, a personalized playlist generation system released in 2022 on the music streaming service Deezer. Track Mix automatically generates "mix" playlists inspired by initial music tracks, allowing users to discover music similar to their favorite content. To generate these mixes, we consider a Transformer model trained on millions of track sequences from user playlists. In light of the growing popularity of Transformers in recent years, we analyze the advantages, drawbacks, and technical challenges of using such a model for mix generation on the service, compared to a more traditional collaborative filtering approach. Since its release, Track Mix has been generating playlists for millions of users daily, enhancing their music discovery experience on Deezer.

* RecSys 2023 - Industry track with oral presentation 
Viaarxiv icon

A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services

Apr 12, 2023
Walid Bendada, Guillaume Salha-Galvan, Thomas Bouabça, Tristan Cazenave

Figure 1 for A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services
Figure 2 for A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services
Figure 3 for A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services
Figure 4 for A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services

Music streaming services often aim to recommend songs for users to extend the playlists they have created on these services. However, extending playlists while preserving their musical characteristics and matching user preferences remains a challenging task, commonly referred to as Automatic Playlist Continuation (APC). Besides, while these services often need to select the best songs to recommend in real-time and among large catalogs with millions of candidates, recent research on APC mainly focused on models with few scalability guarantees and evaluated on relatively small datasets. In this paper, we introduce a general framework to build scalable yet effective APC models for large-scale applications. Based on a represent-then-aggregate strategy, it ensures scalability by design while remaining flexible enough to incorporate a wide range of representation learning and sequence modeling techniques, e.g., based on Transformers. We demonstrate the relevance of this framework through in-depth experimental validation on Spotify's Million Playlist Dataset (MPD), the largest public dataset for APC. We also describe how, in 2022, we successfully leveraged this framework to improve APC in production on Deezer. We report results from a large-scale online A/B test on this service, emphasizing the practical impact of our approach in such a real-world application.

* Accepted as a Full Paper at the SIGIR 2023 conference 
Viaarxiv icon