Recommender embeddings built from multi-view, dynamically pruned cluster centers give modest RMSE gains over classic matrix factorization baselines.
Self-supervised learning for recommender systems: A survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Matrix Factorization with Dynamic Multi-view Clustering for Recommender System
Recommender embeddings built from multi-view, dynamically pruned cluster centers give modest RMSE gains over classic matrix factorization baselines.