5 papers
SPADE: Escaping the Popularity-Similarity Frontier to Measure Serendipitous Recommendations
Tobias Vente, Maarten Peirsman, Noah Daniëls +2
Recommender systems engineer serendipity to foster active exploration and break predictable consumption cycles. The problem with existing offline beyond-accuracy metrics is that th…
What Data is Really Necessary? A Feasibility Study of Inference Data Minimization for Recommender Systems
Jens Leysen, Marco Favier, Bart Goethals
Data minimization is a legal principle requiring personal data processing to be limited to what is necessary for a specified purpose. Operationalizing this principle for recommende…
APS Explorer: Navigating Algorithm Performance Spaces for Informed Dataset Selection
Tobias Vente, Michael Heep, Abdullah Abbas +3
Dataset selection is crucial for offline recommender system experiments, as mismatched data (e.g., sparse interaction scenarios require datasets with low user-item density) can lea…
Discrete-event Tensor Factorization: Learning a Smooth Embedding for Continuous Domains
Joey De Pauw, Bart Goethals
Recommender systems learn from past user behavior to predict future user preferences. Intuitively, it has been established that the most recent interactions are more indicative of…
Weighted Tensor Decompositions for Context-aware Collaborative Filtering
Joey De Pauw, Bart Goethals
Over recent years it has become well accepted that user interest is not static or immutable. There are a variety of contextual factors, such as time of day, the weather or the user…