Timezone: »

Evaluating Graph Generative Models with Contrastively Learned Features
Hamed Shirzad · Kaveh Hassani · Danica J. Sutherland

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #513

A wide range of models have been proposed for Graph Generative Models, necessitating effective methods to evaluate their quality. So far, most techniques use either traditional metrics based on subgraph counting, or the representations of randomly initialized Graph Neural Networks (GNNs). We propose using representations from constrastively trained GNNs, rather than random GNNs, and show this gives more reliable evaluation metrics. Neither traditional approaches nor GNN-based approaches dominate the other, however: we give examples of graphs that each approach is unable to distinguish. We demonstrate that Graph Substructure Networks (GSNs), which in a way combine both approaches, are better at distinguishing the distances between graph datasets.

Author Information

Hamed Shirzad (Simon Fraser University)

I have just started my master's at Simon Fraser University, under the supervision of Prof. Greg Mori. Before here I did my bachelor's in the dual degree of software engineering and mathematics at the Sharif University of Technology in Iran.

Kaveh Hassani (Autodesk Inc)
Danica J. Sutherland (University of British Columbia)

More from the Same Authors