Representation Learning for Heterogeneous Information Networks via Embedding Events
This work addresses a specific bottleneck in network analysis for heterogeneous information networks, offering an incremental improvement by better capturing relation properties.
The paper tackles the problem of ignoring relation properties in heterogeneous information network representation learning by proposing Event2vec, a framework that incorporates both quantities and properties of relations through event-driven proximities, achieving advantages over state-of-the-art algorithms on four real-world datasets and three network analysis tasks.
Network representation learning (NRL) has been widely used to help analyze large-scale networks through mapping original networks into a low-dimensional vector space. However, existing NRL methods ignore the impact of properties of relations on the object relevance in heterogeneous information networks (HINs). To tackle this issue, this paper proposes a new NRL framework, called Event2vec, for HINs to consider both quantities and properties of relations during the representation learning process. Specifically, an event (i.e., a complete semantic unit) is used to represent the relation among multiple objects, and both event-driven first-order and second-order proximities are defined to measure the object relevance according to the quantities and properties of relations. We theoretically prove how event-driven proximities can be preserved in the embedding space by Event2vec, which utilizes event embeddings to facilitate learning the object embeddings. Experimental studies demonstrate the advantages of Event2vec over state-of-the-art algorithms on four real-world datasets and three network analysis tasks (including network reconstruction, link prediction, and node classification).