PKGM: A Pre-trained Knowledge Graph Model for E-commerce Application

TL;DR

PKGM is a pre-trained model that leverages a billion-scale product knowledge graph to provide knowledge services for e-commerce tasks, overcoming data incompleteness and improving task performance.

Contribution

The paper introduces PKGM, a novel pre-trained knowledge graph model that offers uniform item knowledge services without triple data access and handles incomplete graphs effectively.

Findings

PKGM significantly improves performance across five knowledge-related tasks.

Service vectors from PKGM enhance downstream task models.

PKGM effectively addresses data incompleteness issues.

Abstract

In recent years, knowledge graphs have been widely applied as a uniform way to organize data and have enhanced many tasks requiring knowledge. In online shopping platform Taobao, we built a billion-scale e-commerce product knowledge graph. It organizes data uniformly and provides item knowledge services for various tasks such as item recommendation. Usually, such knowledge services are provided through triple data, while this implementation includes (1) tedious data selection works on product knowledge graph and (2) task model designing works to infuse those triples knowledge. More importantly, product knowledge graph is far from complete, resulting error propagation to knowledge enhanced tasks. To avoid these problems, we propose a Pre-trained Knowledge Graph Model (PKGM) for the billion-scale product knowledge graph. On the one hand, it could provide item knowledge services in a uniform way with service vectors for embedding-based and item-knowledge-related task models without accessing triple data. On the other hand, it's service is provided based on implicitly completed product knowledge graph, overcoming the common the incomplete issue. We also propose two general ways to integrate the service vectors from PKGM into downstream task models. We test PKGM in five knowledge-related tasks, item classification, item resolution, item recommendation, scene detection and sequential recommendation. Experimental results show that PKGM introduces significant performance gains on these tasks, illustrating the useful of service vectors from PKGM.