Graph-based Multilingual Product Retrieval in E-commerce Search

TL;DR

This paper presents a universal multilingual product retrieval system for e-commerce search, utilizing graph attention and transformer models to improve cross-lingual retrieval accuracy and operational efficiency across multiple countries.

Contribution

Introduces a multilingual graph attention retrieval network combining transformer and graph neural networks, enabling scalable, cross-lingual product search in e-commerce.

Findings

Outperforms state-of-the-art baselines by 35% recall and 25% mAP.

Significantly increases conversion and revenue in online A/B tests.

Deployed in production for multiple countries, demonstrating practical effectiveness.

Abstract

Nowadays, with many e-commerce platforms conducting global business, e-commerce search systems are required to handle product retrieval under multilingual scenarios. Moreover, comparing with maintaining per-country specific e-commerce search systems, having a universal system across countries can further reduce the operational and computational costs, and facilitate business expansion to new countries. In this paper, we introduce a universal end-to-end multilingual retrieval system, and discuss our learnings and technical details when training and deploying the system to serve billion-scale product retrieval for e-commerce search. In particular, we propose a multilingual graph attention based retrieval network by leveraging recent advances in transformer-based multilingual language models and graph neural network architectures to capture the interactions between search queries and items in e-commerce search. Offline experiments on five countries data show that our algorithm outperforms the state-of-the-art baselines by 35% recall and 25% mAP on average. Moreover, the proposed model shows significant increase of conversion/revenue in online A/B experiments and has been deployed in production for multiple countries.