Most networks aimed towards studying graphs are limited by the size of the graph itself. SAENs (Shift Aggregate Extract Networks) are a novel technique that utilize a deep hierarchical network to break this barrier and allow learning on much larger graphs, especially those with high connectivity like social networks!
SAENs Learn on Large Social Networks with Deep Learning
Post · Mar 17, 2017 18:48 · Share on Twitter
We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested "part-of-part" relations. Unlike recursive neural networks, which unroll a template on input graphs directly, we unroll a neural network template over the decomposition hierarchy, allowing us to deal with the high degree variability that typically characterize social network graphs. Deep hierarchical decompositions are also amenable to domain compression, a technique that reduces both space and time complexity by exploiting symmetries. We show empirically that our approach is competitive with current state-of-the-art graph classification methods, particularly when dealing with social network datasets.