Product Knowledge Graph Embedding for E-commerce

TL;DR

This paper introduces a novel product knowledge graph embedding method tailored for e-commerce, leveraging multi-modal data and advanced embedding techniques to improve knowledge completion, search ranking, and recommendations.

Contribution

It presents a new PKG embedding approach with a self-attention model, multi-task learning, and Poincare embeddings, specifically designed for e-commerce applications.

Findings

Outperforms baselines in knowledge completion tasks.

Enhances search ranking and recommendation accuracy.

Effectively models complex product relations using Poincare embeddings.

Abstract

In this paper, we propose a new product knowledge graph (PKG) embedding approach for learning the intrinsic product relations as product knowledge for e-commerce. We define the key entities and summarize the pivotal product relations that are critical for general e-commerce applications including marketing, advertisement, search ranking and recommendation. We first provide a comprehensive comparison between PKG and ordinary knowledge graph (KG) and then illustrate why KG embedding methods are not suitable for PKG learning. We construct a self-attention-enhanced distributed representation learning model for learning PKG embeddings from raw customer activity data in an end-to-end fashion. We design an effective multi-task learning schema to fully leverage the multi-modal e-commerce data. The Poincare embedding is also employed to handle complex entity structures. We use a real-world dataset from grocery.walmart.com to evaluate the performances on knowledge completion, search ranking and recommendation. The proposed approach compares favourably to baselines in knowledge completion and downstream tasks.