Knowledge Graphs and Machine Learning: A Natural Synergy

Luna Dong, Amazon

Abstract

Knowledge graph is an area with both research breakthroughs and industry success. It plays an important role in Machine Learning, both as a big repository of data to support applications such as search, question answering, and recommendation, and more importantly, as a testbed for ML techniques including data extraction, data integration, data cleaning, text mining, graph embedding, and language understanding.

In this talk, we use Amazon Product Graph as an example to illustrate the challenges in building a knowledge graph and using it in real applications. We will introduce the interesting research problems related to KG, and motivate you why you should use it to power your ML applications and to test your ML techniques.

The slides can be downloaded here.

Bio

Xin Luna Dong is a Principal Scientist at Amazon, leading the efforts of constructing Amazon Product Knowledge Graph. She was one of the major contributors to the Google Knowledge Vault project, and has led the Knowledge-based Trust project, which is called the “Google Truth Machine” by Washington’s Post. She has co-authored book “Big Data Integration”, was awarded ACM Distinguished Member, VLDB Early Career Research Contribution Award for "advancing the state of the art of knowledge fusion", and Best Demo award in Sigmod 2005. She serves in VLDB endowment and PVLDB advisory committee, and is a PC co-chair for VLDB 2021, Sigmod 2018 and WAIM 2015.​​