mlsanityData to 7 Oct 2026

Metadata Embeddings for User and Item Cold-start Recommendations

arXiv 1507.08439 ↗First posted 30 Jul 2015cs.IRcited by 29

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jul 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 9; 2023: 7; 2024: 3; 2025: 3; 2026: 2.

29 papers.

Sort:

By area:

  1. 2023GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretationcited by 101
  2. 2021AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decodingcited by 32
  3. 2022A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendationcited by 22
  4. 2021A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Appscited by 21
  5. 2022Effective and Efficient Training for Sequential Recommendation using Recency Samplingcited by 13
  6. 2024From Variability to Stability: Advancing RecSys Benchmarking Practicescited by 12
  7. 2021Blockchain-based Recommender Systems: Applications, Challenges and Future Opportunitiescited by 11
  8. 2021Dynamic Slate Recommendation with Gated Recurrent Units and Thompson Samplingcited by 5
  9. 2022Online POI Recommendation: Learning Dynamic Geo-Human Interactions in Streamscited by 5
  10. 2021Multimodal Data Fusion in High-Dimensional Heterogeneous Datasets via Generative Modelscited by 3
  11. 2023Private Matrix Factorization with Public Item Featurescited by 3
  12. 2024RePlay: a Recommendation Framework for Experimentation and Production Usecited by 3
17 more
  1. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challengescited by 3
  2. 2026AgentSelect: Benchmark for Narrative Query-to-Agent Recommendationcited by 3
  3. 2023Extreme Multilabel Classification for Specialist Doctor Recommendation with Implicit Feedback and Limited Patient Metadatacited by 2
  4. 2023Towards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attackscited by 2
  5. 2024Generalized User Representations for Transfer Learningcited by 2
  6. 2022Exploring Customer Price Preference and Product Profit Role in Recommender Systemscited by 1
  7. 2022Dynamic collaborative filtering Thompson Sampling for cross-domain advertisements recommendationcited by 1
  8. 2022Tag-Aware Document Representation for Research Paper Recommendationcited by 1
  9. 2025M-LLM3REC: A Motivation-Aware User-Item Interaction Framework for Enhancing Recommendation Accuracy with LLMscited by 1
  10. 2022Gender In Gender Out: A Closer Look at User Attributes in Context-Aware Recommendationcited by 0
  11. 2022Beer2Vec : Extracting Flavors from Reviews for Thirst-Quenching Recommandationscited by 0
  12. 2022Lib-SibGMU -- A University Library Circulation Dataset for Recommender Systems Developmencited by 0
  13. 2023Job recommendations: benchmarking of collaborative filtering methods for classifiedscited by 0
  14. 2023Predicting IPv4 Services Across All Portscited by 0
  15. 2023MFAI: A Scalable Bayesian Matrix Factorization Approach to Leveraging Auxiliary Informationcited by 0
  16. 2025On the Reliability of Sampling Strategies in Offline Recommender Evaluationcited by 0
  17. 2026Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbookcited by 0