Metadata Embeddings for User and Item Cold-start Recommendations

2015/07/30 by Maciej Kula, Kula, Maciej · 5 citations
Computer Science · #FOS: Computer and information sciences #H.3.3 #Information Retrieval (cs.IR) #cs.IR

paper · pdf · doi:10.48550/arxiv.1507.08439

arxiv created 2015/07/30 · arxiv updated 2015/07/31

Abstract

I present a hybrid matrix factorisation model representing users and items as linear combinations of their content features' latent factors. The model outperforms both collaborative and content-based models in cold-start or sparse interaction data scenarios (using both user and item metadata), and performs at least as well as a pure collaborative matrix factorisation model where interaction data is abundant. Additionally, feature embeddings produced by the model encode semantic information in a way reminiscent of word embedding approaches, making them useful for a range of related tasks such as tag recommendations.

Cited by

• Drug-disease networks and drug repurposing
• M-LLM³REC: A Motivation-Aware User-Item Interaction Framework for Enhancing Recommendation Accuracy with LLMs
• Encode Me If You Can: Learning Universal User Representations via Event Sequence Autoencoding
• On the Reliability of Sampling Strategies in Offline Recommender Evaluation
• A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges

Related

• Cross-Attribute Matrix Factorization Model with Shared User Embedding
• MARec: Metadata Alignment for cold-start Recommendation
• Cold-start recommendations in Collective Matrix Factorization
• Do LLMs Understand Collaborative Signals? Diagnosis and Repair
• Maximum Impact with Fewer Features: Efficient Feature Selection for Cold-Start Recommenders through Collaborative Importance Weighting