Toward Edge-Centric Network Embeddings

Abstract

Existing network embedding approaches tackle the problem of learning low-dimensional node representations. However, networks can also be seen in the light of edges interlinking pairs of nodes. The broad goal of this paper is to introduce edge-centric network embeddings. We present an approach called ECNE, which instead of computing node embeddings directly, computes edge embeddings by relying on the notion of line graph coupled with an edge weighting mechanism to preserve the dynamic of the original graph in the line graph. We also present a link prediction framework called ECNE-LP, which given a target link (u,v) first collects paths between nodes u and v, then directly embeds the edges in these paths, and finally aggregates them toward predicting the existence of a link. We show that both ECNE and ECNE-LP bring benefit wrt the state-of-the-art.

References in corpus (10)

• Distributed Representations of Words and Phrases and their Compositionality
• Modularity and community structure in networks
• Inductive Representation Learning on Large Graphs
• Link communities reveal multiscale complexity in networks
• Graph Embedding Techniques, Applications, and Performance: A Survey
• struc2vec: Learning Node Representations from Structural Identity
• Line Graphs, Link Partitions and Overlapping Communities
• MILE: A Multi-Level Framework for Scalable Graph Embedding
• Clustering under the line graph transformation: Application to reaction network
• Learning Edge Properties in Graphs from Path Aggregations