Generations of Knowledge Graphs: The Crazy Ideas and the Business Impact

TL;DR

This paper explores the evolution of knowledge graphs across three generations, highlighting innovative ideas and their significant impact on industry applications like search, recommendations, and integration with large language models.

Contribution

It introduces the concept of three generations of knowledge graphs, detailing their characteristics, innovative construction ideas, and their role in advancing both scientific research and business practices.

Findings

Entity-based KGs support search and question answering.

Text-rich KGs enhance search and recommendations.

Integration of KGs with LLMs creates dual neural KGs.

Abstract

Knowledge Graphs (KGs) have been used to support a wide range of applications, from web search to personal assistant. In this paper, we describe three generations of knowledge graphs: entity-based KGs, which have been supporting general search and question answering (e.g., at Google and Bing); text-rich KGs, which have been supporting search and recommendations for products, bio-informatics, etc. (e.g., at Amazon and Alibaba); and the emerging integration of KGs and LLMs, which we call dual neural KGs. We describe the characteristics of each generation of KGs, the crazy ideas behind the scenes in constructing such KGs, and the techniques developed over time to enable industry impact. In addition, we use KGs as examples to demonstrate a recipe to evolve research ideas from innovations to production practice, and then to the next level of innovations, to advance both science and business.