Integrates contextual constraints into embedding-based recommendation models by jointly learning constraint representations with user and item embeddings, reporting improved predictive performance on matrix factorization models.
A survey of collaborative filtering techniques
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Authors propose block-based SVD matrix factorization (BMF) for scalable recommender systems using CUDA and GPUs to improve performance and memory use.
citing papers explorer
-
Embedding models for recommendation under contextual constraints
Integrates contextual constraints into embedding-based recommendation models by jointly learning constraint representations with user and item embeddings, reporting improved predictive performance on matrix factorization models.
-
Block based Singular Value Decomposition approach to matrix factorization for recommender systems
Authors propose block-based SVD matrix factorization (BMF) for scalable recommender systems using CUDA and GPUs to improve performance and memory use.