E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914347229380608 |
|---|---|
| author | Kang, Jiwoo Lee, Yeon-Chang |
| author_facet | Kang, Jiwoo Lee, Yeon-Chang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20877 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications Kang, Jiwoo Lee, Yeon-Chang Information Retrieval Artificial Intelligence 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. |
| title | E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2602.20877 |