Cross-platform Product Matching Based on Knowledge Graph

Abstract

Product matching aims to identify similar or identical products sold on different platforms, which is crucial for retailers to adjust investment strategies. By building knowledge graphs (KGs), the product matching problem can be converted to the Entity Alignment (EA) task, which aims to discover the equivalent entities from diverse KGs. This paper introduces a two-stage pipeline consisted of rough filter and fine filter. Based on product names and categories, we roughly match products in rough filtering. For fine filtering, a new framework for Entity Alignment, Relation-aware, and Attribute-aware Graph Attention Networks for Entity Alignment (RAEA), is employed. Experiments on eBay-Amazon dataset indicated that the two-stage pipeline performs well on the problem of cross-platform product matching.