Multi-modal clothing recommendation model based on large model and VAE enhancement

TL;DR

This paper introduces a multimodal clothing recommendation system that combines text and image analysis with large language models and VAE to improve accuracy and address cold start issues.

Contribution

It presents a novel multimodal analysis framework integrating large language models and VAE, enhancing clothing recommendation performance and cold start problem mitigation.

Findings

Significant performance improvements over existing methods.

Effective handling of cold start problem.

Validated through extensive ablation experiments.

Abstract

Accurately recommending products has long been a subject requiring in-depth research. This study proposes a multimodal paradigm for clothing recommendations. Specifically, it designs a multimodal analysis method that integrates clothing description texts and images, utilizing a pre-trained large language model to deeply explore the hidden meanings of users and products. Additionally, a variational encoder is employed to learn the relationship between user information and products to address the cold start problem in recommendation systems. This study also validates the significant performance advantages of this method over various recommendation system methods through extensive ablation experiments, providing crucial practical guidance for the comprehensive optimization of recommendation systems.