We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradient-based learning algorithms to systems composed of modules th...
We describe a method for proving the termination of graph transformation systems. The method is based on the fact that infinite reductions must include infinite `creation chains...
We define transactional graph transformation systems (t-gtss), a mild extension of the ordinary framework for the double-pushout approach to graph transformation, which allows to ...
Paolo Baldan, Andrea Corradini, Fernando Luí...
We present a unified framework for learning link prediction and edge weight prediction functions in large networks, based on the transformation of a graph's algebraic spectru...
: TGraphs are directed graphs with typed, attributed, and ordered nodes and edges. These properties leverage the use of graphs as models for all kinds of artifacts in the context o...