Regularizing Matrix Factorization with User and Item Embeddings for Recommendation
This work addresses recommendation accuracy for users and items, particularly in cold-start settings, but is incremental as it builds on existing latent factor and embedding approaches.
The paper tackles the problem of improving recommendation systems by proposing a Regularized Multi-Embedding (RME) model that integrates multiple user and item interaction patterns, resulting in significant performance gains such as Recall@5 improvements of 5.9-7.0% and NDCG@5 boosts of 20.2-29.4% in cold-start scenarios.
Following recent successes in exploiting both latent factor and word embedding models in recommendation, we propose a novel Regularized Multi-Embedding (RME) based recommendation model that simultaneously encapsulates the following ideas via decomposition: (1) which items a user likes, (2) which two users co-like the same items, (3) which two items users often co-liked, and (4) which two items users often co-disliked. In experimental validation, the RME outperforms competing state-of-the-art models in both explicit and implicit feedback datasets, significantly improving Recall@5 by 5.9~7.0%, NDCG@20 by 4.3~5.6%, and MAP@10 by 7.9~8.9%. In addition, under the cold-start scenario for users with the lowest number of interactions, against the competing models, the RME outperforms NDCG@5 by 20.2% and 29.4% in MovieLens-10M and MovieLens-20M datasets, respectively. Our datasets and source code are available at: https://github.com/thanhdtran/RME.git.