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

TL;DR

E-MMKGR introduces a unified multimodal knowledge graph framework for e-commerce that enhances recommendation and search tasks by providing extensible, task-agnostic item representations using GNNs and knowledge graph optimization.

Contribution

The paper presents E-MMKGR, a novel framework that constructs an e-commerce-specific multimodal knowledge graph and learns unified item representations for diverse tasks.

Findings

Up to 10.18% improvement in Recall@10 for recommendations

Up to 21.72% improvement in vector-based product search

Effective and extensible approach demonstrated on Amazon datasets

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.