Graphs are ubiquitous in encoding relational information of real-world objects in many
domains. Graph generation, whose purpose is to generate new graphs from a distribution …

Melanoma is the fifth most common cancer in the United States. Conventional drug
discovery methods are inherently time-consuming and costly, which imposes significant …

Deep learning on graphs has gained interest in recent years. The applicability of graphs to
model problems in various domains, such as chemical molecules, financial transactions …

The performance of learning based algorithms largely depends on the given representation
of data. Therefore the questions arise, i) how to obtain useful representations, ii) how to …