MultiplexSAGE: A Multiplex Embedding Algorithm for Inter-Layer Link Prediction

Research on graph representation learning has received great attention in recent years. However, most of the studies so far have focused on the embedding of single-layer graphs. The few studies dealing with the problem of representation learning of multilayer structures rely on the strong hypothesis that the inter-layer links are known, and this limits the range of possible applications. Here we propose MultiplexSAGE, a generalization of the GraphSAGE algorithm that allows embedding multiplex networks. We show that MultiplexSAGE is capable to reconstruct both the intra-layer and the inter-layer connectivity, outperforming competing methods. Next, through a comprehensive experimental analysis, we shed light also on the performance of the embedding, both in simple and multiplex networks, showing that both the density of the graph and the randomness of the links strongly influences the quality of the embedding.

Automated summary

Research on graph representation learning has been highly focused on single-layer graphs, and there is limited research on representation learning of multilayer structures without known inter-layer links. This study proposes MultiplexSAGE, a generalized algorithm capable of embedding multiplex networks and reconstructing intra-layer and inter-layer connectivity. Experimental analysis reveals that the quality of embedding is strongly influenced by the density and randomness of the graph's links in both simple and multiplex networks.