XWalk: Random Walk Based Candidate Retrieval for Product Search

TL;DR

XWalk is a graph-based candidate retrieval method for product search that significantly enhances head query performance in e-commerce, outperforming neural retrievers and benefiting from ensembling with other methods.

Contribution

Introduces XWalk, a scalable random-walk graph approach for product candidate retrieval that improves head query results beyond existing neural methods.

Findings

XWalk outperforms state-of-the-art neural retrievers in head query performance.

Ensembling XWalk with neural or lexical retrievers yields superior overall retrieval results.

XWalk is efficient for training and inference in large-scale e-commerce settings.

Abstract

In e-commerce, head queries account for the vast majority of gross merchandise sales and improvements to head queries are highly impactful to the business. While most supervised approaches to search perform better in head queries vs. tail queries, we propose a method that further improves head query performance dramatically. We propose XWalk, a random-walk based graph approach to candidate retrieval for product search that borrows from recommendation system techniques. XWalk is highly efficient to train and inference in a large-scale high traffic e-commerce setting, and shows substantial improvements in head query performance over state-of-the-art neural retreivers. Ensembling XWalk with a neural and/or lexical retriever combines the best of both worlds and the resulting retrieval system outperforms all other methods in both offline relevance-based evaluation and in online A/B tests.