Persona2vec: A Flexible Multi-role Representations Learning Framework for Graphs
This addresses the limitation of single-vector node embeddings in graph mining for domains with overlapping communities, offering an incremental improvement over existing methods.
The paper tackles the problem of nodes in graphs belonging to multiple communities by proposing persona2vec, a framework for learning multiple representations per node, and shows it is significantly faster and achieves better performance than the state-of-the-art in link prediction.
Graph embedding techniques, which learn low-dimensional representations of a graph, are achieving state-of-the-art performance in many graph mining tasks. Most existing embedding algorithms assign a single vector to each node, implicitly assuming that a single representation is enough to capture all characteristics of the node. However, across many domains, it is common to observe pervasively overlapping community structure, where most nodes belong to multiple communities, playing different roles depending on the contexts. Here, we propose persona2vec, a graph embedding framework that efficiently learns multiple representations of nodes based on their structural contexts. Using link prediction-based evaluation, we show that our framework is significantly faster than the existing state-of-the-art model while achieving better performance.