AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction
Pollawat Hongwimol, Haoning Shang, Chutong Wang, Zhichao Wan, Yi Gao, Yuanming Li, Lin Gui, Wenhao Sun, Cheng Yu

TL;DR
AutoPKG is an innovative multi-agent LLM framework that automatically constructs and maintains a dynamic product-attribute knowledge graph from multimodal e-commerce content, enhancing attribute extraction and increasing marketplace GMV.
Contribution
The paper introduces AutoPKG, a novel multi-agent LLM framework for automatic, dynamic construction and maintenance of product-attribute knowledge graphs in e-commerce.
Findings
Achieves up to 0.953 WKE for product types on Lazada data.
Improves attribute extraction F1 score by 0.152 on public benchmarks.
Increases GMV in production by up to 7.89% through derived attributes.
Abstract
Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. We present AutoPKG, a multi-agent Large Language Model (LLM) framework that automatically constructs a Product-attribute Knowledge Graph (PKG) from multimodal product content. AutoPKG induces product types and type-specific attribute keys on demand, extracts attribute values from text and images, and consolidates updates through a centralized decision agent that maintains a globally consistent canonical graph. We also propose an evaluation protocol for dynamic PKGs that measures type and key validity, consolidation quality, and edge-level accuracy for value assertions after canonicalization. On a large real-world marketplace catalog dataset from Lazada (Alibaba), AutoPKG achieves up to 0.953 Weighted Knowledge Efficiency (WKE) for product types, 0.724 WKE…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
