Cross-platform Product Matching Based on Entity Alignment of Knowledge Graph with RAEA model
Wenlong Liu, Jiahua Pan, Xingyu Zhang, Xinxin Gong, Yang Ye, Xujin Zhao, Xin Wang, Kent Wu, Hua Xiang, Houmin Yan, Qingpeng Zhang
TL;DR
This work frames cross-platform product matching as cross-knowledge-graph entity alignment, addressing the limited integration of attribute and relation signals in prior methods. It introduces RAEA, a relation- and attribute-aware graph attention framework that models interactions between attributes and relations and preserves relation-type diversity, embedded within a two-stage pipeline (rough filtering + fine filtering). The approach demonstrates strong performance on the eBay–Amazon dataset (NDCG ~0.566) and achieves competitive or state-of-the-art results on public EA benchmarks (DBP15K and DWY100K), with a pre-weighted ensemble further boosting accuracy. The method leverages a MPnet-based attribute encoder, SimCSE pretraining, and a multi-channel architecture to produce high-quality entity alignments, supported by ablations underscoring the value of each component and the ensemble strategy.
Abstract
Product matching aims to identify identical or similar products sold on different platforms. 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. The existing EA methods inadequately utilize both attribute triples and relation triples simultaneously, especially the interactions between them. This paper introduces a two-stage pipeline consisting of rough filter and fine filter to match products from eBay and Amazon. For fine filtering, a new framework for Entity Alignment, Relation-aware and Attribute-aware Graph Attention Networks for Entity Alignment (RAEA), is employed. RAEA focuses on the interactions between attribute triples and relation triples, where the entity representation aggregates the alignment signals from attributes and relations with Attribute-aware Entity Encoder and Relation-aware Graph Attention Networks. The experimental results indicate that the RAEA model achieves significant improvements over 12 baselines on EA task in the cross-lingual dataset DBP15K (6.59% on average Hits@1) and delivers competitive results in the monolingual dataset DWY100K. The source code for experiments on DBP15K and DWY100K is available at github (https://github.com/Mockingjay-liu/RAEA-model-for-Entity-Alignment).