Learning representations of sets of nodes in a graph is crucial for applications ranging from node-role discovery to link prediction and molecule classification.

Deep predictive models of neuronal activity have recently enabled several new discoveries about the selectivity and invariance of neurons in the visual cortex.

Scientific discoveries areadvancing atanever-growing rate, with tensofthousands ofnewpapers added just to arXiv every month [4]. This rapid progress has led to information overload within communities, making it nearly impossible for scientists to read all relevant papers.