Graph of Graphs: A New Knowledge Representation Mechanism for Graph Learning (Student Abstract)


  • Zhwiei Zhen University of Texas at Dallas
  • Yuzhou Chen Temple University
  • Murat Kantarcioglu University of Texas at Dallas
  • Yulia R. Gel University of Texas at Dallas



Graph Classification, Graph Learning, Knowledge Representation


Supervised graph classification is one of the most actively developing areas in machine learning (ML), with a broad range of domain applications, from social media to bioinformatics. Given a collection of graphs with categorical labels, the goal is to predict correct classes for unlabelled graphs. However, currently available ML tools view each such graph as a standalone entity and, as such, do not account for complex interdependencies among graphs. We propose a novel knowledge representation for graph learning called a {\it Graph of Graphs} (GoG). The key idea is to construct a new abstraction where each graph in the collection is represented by a node, while an edge then reflects similarity among the graphs. Such similarity can be assessed via a suitable graph distance. As a result, the graph classification problem can be then reformulated as a node classification problem. We show that the proposed new knowledge representation approach not only improves classification performance but substantially enhances robustness against label perturbation attacks.




How to Cite

Zhen, Z., Chen, Y., Kantarcioglu, M., & Gel, Y. R. (2023). Graph of Graphs: A New Knowledge Representation Mechanism for Graph Learning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16386-16387.