Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications

Jiwoo Kang, Yeon-Chang Lee

TL;DR

E-MMKGR is proposed, a framework that constructs an e-commerce-specific Multimodal Knowledge Graph E-MMKG and learns unified item representations through GNN-based propagation and KG-oriented optimization and provides a shared semantic foundation applicable to diverse tasks.

Abstract

Multimodal recommender systems (MMRSs) enhance collaborative filtering by leveraging item-side modalities, but their reliance on a fixed set of modalities and task-specific objectives limits both modality extensibility and task generalization. We propose E-MMKGR, a framework that constructs an e-commerce-specific Multimodal Knowledge Graph E-MMKG and learns unified item representations through GNN-based propagation and KG-oriented optimization. These representations provide a shared semantic foundation applicable to diverse tasks. Experiments on real-world Amazon datasets show improvements of up to 10.18% in Recall@10 for recommendation and up to 21.72% over vector-based retrieval for product search, demonstrating the effectiveness and extensibility of our approach.

E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications

TL;DR

E-MMKGR is proposed, a framework that constructs an e-commerce-specific Multimodal Knowledge Graph E-MMKG and learns unified item representations through GNN-based propagation and KG-oriented optimization and provides a shared semantic foundation applicable to diverse tasks.

Abstract

Multimodal recommender systems (MMRSs) enhance collaborative filtering by leveraging item-side modalities, but their reliance on a fixed set of modalities and task-specific objectives limits both modality extensibility and task generalization. We propose E-MMKGR, a framework that constructs an e-commerce-specific Multimodal Knowledge Graph E-MMKG and learns unified item representations through GNN-based propagation and KG-oriented optimization. These representations provide a shared semantic foundation applicable to diverse tasks. Experiments on real-world Amazon datasets show improvements of up to 10.18% in Recall@10 for recommendation and up to 21.72% over vector-based retrieval for product search, demonstrating the effectiveness and extensibility of our approach.
Paper Structure (10 sections, 7 equations, 3 figures, 4 tables)

This paper contains 10 sections, 7 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. E-MMKG Construction
  5. Unified Representation Learning
  6. Downstream Applications
  7. Evaluation
  8. Experimental Setup
  9. Experimental Results
  10. Conclusion

Figures (3)

  • Figure 1: General MMKG and the proposed E-MMKG.
  • Figure 2: Overview of the E-MMKGR framework.
  • Figure 3: t-SNE visualization of unified item representations for Clothing with K-means clustering