Skip to main navigation Skip to search Skip to main content

Progressive Fusion of LLM-Augmented Multi-Modal Data for Enhanced Product Recommendations

  • Xinhao Li
  • , Lin Gong
  • , Xin Liu*
  • , Xi Xiang
  • *Corresponding author for this work
  • Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Recommender systems in E-commerce often face challenges such as data sparsity and cold-start problems, which hinder their ability to provide accurate and personalized recommendations. To address these issues, we propose Progressive Fusion Muti-modal Graph Convolution Networks (PFMGCN), a novel framework tailored for product recommendations. In PFMGCN, we first employ a Large Language Model (LLM) to generate more product attribute data for enriching contextual information. A knowledge graph (KG) is then constructed with augmented nodes, and their embeddings are extracted via pre-trained models. A cross-attention module is used to dynamically fuse textual and visual features, capturing fine-grained product details. Progressive graph convolutional networks integrated with multi-modal cross-attention are then applied to extract deep features and deliver accurate recommendations. Extensive experiments on real-world E-commerce datasets demonstrate that our approach significantly outperforms state-of-the-art methods, achieving superior accuracy in product recommendation tasks.

Original languageEnglish
Title of host publication2025 IEEE 6th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2047-2050
Number of pages4
ISBN (Electronic)9798331522285
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event6th IEEE International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2025 - Shenzhen, China
Duration: 11 Apr 2025 → 13 Apr 2025

Publication series

Name2025 IEEE 6th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2025

Conference

Conference6th IEEE International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2025
Country/TerritoryChina
CityShenzhen
Period11/04/25 → 13/04/25

Keywords

  • cross-attention
  • knowledge graph
  • large language model
  • multi-modality
  • recommender system

Fingerprint

Dive into the research topics of 'Progressive Fusion of LLM-Augmented Multi-Modal Data for Enhanced Product Recommendations'. Together they form a unique fingerprint.

Cite this