A Neural Matrix Decomposition Recommender System Model based on the Multimodal Large Language Model

TL;DR

This paper introduces BoNMF, a neural matrix factorization recommendation model leveraging multimodal large language models like BoBERTa and ViT, significantly enhancing recommendation accuracy especially in cold start scenarios.

Contribution

The paper presents a novel multimodal neural matrix decomposition model that combines NLP and vision models for improved recommendation performance.

Findings

BoNMF outperforms existing models on public datasets.

Significant improvement in cold start recommendation accuracy.

Effective integration of multimodal data enhances recommendation quality.

Abstract

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.