11 papers
Fully Deterministic Shallow Neural Networks with Localized Activations. Part I: Construction and Optimal Sobolev Approximation
Ran Bi, Weibing Deng
We construct shallow neural networks with fixed Gaussian and tanh-difference activations on bounded Lipschitz domains , . For each , explicit dete…
Privacy in Personalized AI Is a System Property, Not Just a Model Property
Guillaume Salha-Galvan, Jiaying Xu
In personalized AI applications, such as conversational assistants and recommender systems, users interact not with models in isolation but with broader systems that access, infer,…
Music Playlist Captioning at Scale with Large Language Models
Mathieu Delcluze, Léa Briand, Benjamin Chapus +2
Music streaming services such as Deezer often recommend personalized playlists to users. Playlist captioning, which involves describing these playlists in natural language, is esse…
IDProxy: CTR Prediction with Multimodal LLMs for Cold-Start Recommendation at Xiaohongshu
Yubin Zhang, Haiming Xu, Guillaume Salha-Galvan +6
Content-driven platforms such as Xiaohongshu often leverage click-through rate (CTR) prediction models for recommendation. However, these models depend heavily on item ID embedding…
MusicSem: A Semantically Rich Language--Audio Dataset of Natural Music Descriptions
Rebecca Salganik, Teng Tu, Fei-Yueh Chen +8
Music representation learning is central to music information retrieval and generation. While recent advances in multimodal learning have improved alignment between text and audio…
FairExpand: Individual Fairness on Graphs with Partial Similarity Information
Rebecca Salganik, Yibin Wang, Guillaume Salha-Galvan +1
Individual fairness, which requires that similar individuals should be treated similarly by algorithmic systems, has become a central principle in fair machine learning. Individual…
Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling
Walid Bendada, Guillaume Salha-Galvan, Romain Hennequin +3
This paper introduces von Mises-Fisher exploration (vMF-exp), a scalable method for exploring large action sets in reinforcement learning problems where hyperspherical embedding ve…
To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoders
Guillaume Salha-Galvan, Jiaying Xu
This paper investigates the understudied practice of weight sharing (WS) in variational graph autoencoders (VGAE). WS presents both benefits and drawbacks for VGAE model design and…
Transformers Meet ACT-R: Repeat-Aware and Sequential Listening Session Recommendation
Viet-Anh Tran, Guillaume Salha-Galvan, Bruno Sguerra +1
Music streaming services often leverage sequential recommender systems to predict the best music to showcase to users based on past sequences of listening sessions. Nonetheless, mo…
Do Recommender Systems Promote Local Music? A Reproducibility Study Using Music Streaming Data
Kristina Matrosova, Lilian Marey, Guillaume Salha-Galvan +3
This paper examines the influence of recommender systems on local music representation, discussing prior findings from an empirical study on the LFM-2b public dataset. This prior s…
Let's Get It Started: Fostering the Discoverability of New Releases on Deezer
Léa Briand, Théo Bontempelli, Walid Bendada +5
This paper presents our recent initiatives to foster the discoverability of new releases on the music streaming service Deezer. After introducing our search and recommendation feat…