In this episode of ACM ByteCast, Bruke Kifle hosts ACM and IEEE Fellow Xin Luna Dong, Principal Scientist at Meta Reality Labs. She has significantly contributed to the development of knowledge graphs, a tool essential for organizing data into understandable relationships. Prior to joining Meta, Luna spent nearly a decade working on knowledge graphs at Amazon and Google. Before that, she spent another decade working on data integration and cleaning at AT&T Labs. She has been a leader in ML applications, working on intelligent personal assistants, search, recommendation, and personalization systems, including products such as Ray-Ban Meta. Her honors and recognitions include the VLDB Women in Database Research Award and the VLDB Early Career Research Contribution Award.
Luna shares how early experiences growing up in China sparked her interest in computing, and how her PhD experience in data integration lay the groundwork for future work with knowledge graphs. Luna and Bruke dive into the relevance and structure of knowledge graphs, and her work on Google Knowledge Graph and Amazon Product Knowledge Graph. She talks about the progression of data integration methodologies over the past two decades, how the rise of ML and AI has given rise to a new one, and how knowledge graphs can enhance LLMs. She also mentions promising emerging technologies for answer generation and recommender systems such as Retrieval-Augmented Generation (RAG), and her work on the Comprehensive RAG Benchmark (CRAC) and the KDD Cup competition. Luna also shares her passion for making information access effortless, especially for non-technical users such as small business owners, and suggests some solutions.
