5 papers
Leveraging Artist Catalogs for Cold-Start Music Recommendation
Yan-Martin Tamm, Gregor Meehan, VojtÄch Nekl +4
The item cold-start problem poses a fundamental challenge for music recommendation: newly added tracks lack the interaction history that collaborative filtering (CF) requires. Exis…
Efficient Learning of Sparse Representations from Interactions
VojtÄch VanÄura, Martin Spišák, Rodrigo Alves +1
Behavioral patterns captured in embeddings learned from interaction data are pivotal across various stages of production recommender systems. However, in the initial retrieval stag…
From Knots to Knobs: Towards Steerable Collaborative Filtering Using Sparse Autoencoders
Martin Spišák, Ladislav Peška, Petr Škoda +2
Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different l…
The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems
Petr Kasalický, Martin Spišák, VojtÄch VanÄura +3
Industry-scale recommender systems face a core challenge: representing entities with high cardinality, such as users or items, using dense embeddings that must be accessible during…
beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems
VojtÄch VanÄura, Pavel KordÃk, Milan Straka
Recommender systems often use text-side information to improve their predictions, especially in cold-start or zero-shot recommendation scenarios, where traditional collaborative fi…