PhD. defense at the Department of Computer Science, Aalborg University

#Explainable #and #Reliable #Graph #Neural #Networks
Share

Graph Neural Networks (GNNs) have emerged as a powerful paradigm for learning from complex graph-structured data, yet their opaque decision processes hinder trustworthy deployment in high-stakes applications. This dissertation advances the foundations of explainable and reliable GNN reasoning through four interrelated studies, forming a cohesive framework for interpretable, robust, and multi-faceted GNN explanations. Together, these works bridge theoretical understanding, algorithmic development, and practical evaluation of GNN explainability.


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar

Loading virtual attendance info...

  • Contact Event Host

  • byang@ieee.org

  • Co-sponsored by Sean Bin Yang

  Speakers

Dazhuo Qiu of Aalborg University

Topic:

Toward Explainable and Reliable Graph Neural Networks: A Data-Driven Perspective

Graph Neural Networks (GNNs) have emerged as a powerful paradigm for learning from complex graph-structured data, yet their opaque decision processes hinder trustworthy deployment in high-stakes applications. This dissertation advances the foundations of explainable and reliable GNN reasoning through four interrelated studies, forming a cohesive framework for interpretable, robust, and multi-faceted GNN explanations. Together, these works bridge theoretical understanding, algorithmic development, and practical evaluation of GNN explainability.

Biography:

Dazhuo Qiu is a PhD fellow in Department of Computer Science at Aalborg University. His research interest is explainable graph neural network.

Email:

Address:Selma Lagerløfs Vej 300, , Aalborg, Denmark, 9220