A Neural Matrix Decomposition Recommender System Model based on the Multimodal Large Language Model
This work addresses recommendation accuracy and cold start issues for users of recommendation systems, representing an incremental improvement through hybrid integration of existing techniques.
The paper tackles recommendation system accuracy by proposing BoNMF, a neural matrix factorization model that integrates multimodal large language models (BoBERTa and ViT) with neural matrix decomposition. Experimental results show the model significantly improves recommendation accuracy on large public datasets and addresses cold start problems.
Recommendation systems have become an important solution to information search problems. This article proposes a neural matrix factorization recommendation system model based on the multimodal large language model called BoNMF. This model combines BoBERTa's powerful capabilities in natural language processing, ViT in computer in vision, and neural matrix decomposition technology. By capturing the potential characteristics of users and items, and after interacting with a low-dimensional matrix composed of user and item IDs, the neural network outputs the results. recommend. Cold start and ablation experimental results show that the BoNMF model exhibits excellent performance on large public data sets and significantly improves the accuracy of recommendations.