Efficient Evaluation of Knowledge Graph Quality: Challenges and Opportunities

Efficient Evaluation of Knowledge Graph Quality: Challenges and Opportunities


09 May 2025
11:00

Abstract

Knowledge Graphs (KGs) play a vital role in data-driven applications such as virtual assistants, recommendation systems, and semantic search. The accuracy and reliability of these applications depend on the quality of the underlying KGs, making their evaluation crucial. However, manually assessing the quality of large-scale KGs is prohibitively expensive, requiring efficient strategies that minimize human annotation while ensuring guarantees on the assessments. Despite its importance, this challenge has received limited attention. This seminar presents recent advances in KG quality evaluation, introducing advanced sampling techniques and robust statistical methods that enhance reliability and efficiency. Particular attention is paid to the choice of the statistical intervals used to quantify the uncertainties associated with sampling. The seminar also examines real-world applications and outlines current challenges and limitations, particularly in dynamic environments where KG contents evolve over time.

Speakers

  • Stefano Marchesin
    Università degli Studi di Padova
    HOMEPAGE

    Stefano Marchesin is Assistant Professor at the Department of Information Engineering of the University of Padua. His educational background includes a Bachelor's degree in Information Engineering, a Master's degree in Computer Engineering, and a Ph.D. in Information Engineering. He is member of the Intelligent Interactive Information Access (IIIA) HUB. His research interests lie in data quality, information extraction, and information retrieval. He published 50+ scientific papers in national and international venues, including VLDB, SIGMOD, SIGIR, CIKM, TOIS, and IP&M.