Hierarchical Knowledge Graph Construction from Images for Scalable E-Commerce
This addresses the need for efficient, low-cost automated knowledge graph construction in e-commerce, enabling timely updates and supporting downstream applications, though it appears incremental in method integration.
The paper tackles the problem of constructing structured product knowledge graphs from raw product images for e-commerce by proposing a novel method that leverages vision-language and large language models, achieving outperformance over baselines in all metrics and properties.
Knowledge Graph (KG) is playing an increasingly important role in various AI systems. For e-commerce, an efficient and low-cost automated knowledge graph construction method is the foundation of enabling various successful downstream applications. In this paper, we propose a novel method for constructing structured product knowledge graphs from raw product images. The method cooperatively leverages recent advances in the vision-language model (VLM) and large language model (LLM), fully automating the process and allowing timely graph updates. We also present a human-annotated e-commerce product dataset for benchmarking product property extraction in knowledge graph construction. Our method outperforms our baseline in all metrics and evaluated properties, demonstrating its effectiveness and bright usage potential.