Owing to their versatility, graph structures admit representations of intricate relationships between the separate entities comprising the data. We formalise the notion of connection between two vertex sets in terms of edge and vertex features by introducing graph-walking programs. We give two algorithms for mining of deterministic graph-walking programs that yield programs in the order of increasing length. These programs characterise linear long-distance relationships between the given two vertex sets in the context of the whole graph.

Deep Learning has become a trend that everyone is attempting to enforce in many problems as it has proved its success in solving many problems with extremely high accuracy. Even though deep learning is highly effective, many problems could have been solved with exact programs and classical computer science techniques. Does deep learning actually get applied where it should? Do people experiment with other techniques before turning to deep learning when solving a problem? In this article, we attempt to answer these questions with the help of two actual examples.