Event Navigation
Thesis Information
Title: Id-Gnn: Unsupervised Gnn For Heterophilic Graphs
Program: Master of Science in Computer Science
Advisor: Dr. Edoardo Serra, Computer Science
Committee Members: Dr. Francesca Spezzano, Computer Science and Dr. Marion Scheepers, Mathematics
Abstract
Graph-structured data has increasing applicability in hundreds of domains, the majority of which produce mostly unlabeled data. For this reason, the supervised methods of graph representation learning, which dominate current methods, have limited use in many cases. Similarly, many methods rely on a graph being homophilic in which proximity implies similarity. In many applications, the structure of a node’s connections carries more relevant information than the nodes to which it is connected. The proposed method is an unsupervised graph neural network which doesn’t rely on homophily of the graphs. It creates an identifying signature for each node and supplements each node’s features with the IDs of its neighbots to encourage representations that can be used to reconstruct the features of the neighbors. The produced representations may be used in downstream tasks such as node classification.
