A survey on heterogeneous network representation learning

Heterogeneous information networks usually contain different kinds of nodes and distinguishing types of relations, which can preserve more information than homogeneous information networks. Heteroge-neous network representation learning attempts to learn a low-dimensional representation for each node and capture rich semantic information of the given network. Most of existing surveys focus on hetero-geneous information network analysis and homogeneous information network representation learning. Although considerable research efforts concentrate on heterogeneous network representation learning, there are few surveys that systematically review the state-of-the-art heterogeneous network represen-tation learning techniques. Motivated by this, we propose a taxonomy of heterogeneous network rep-resentation learning algorithms according to different approaches of capturing semantic information in heterogeneous networks, including path based algorithms and semantic unit based algorithms. Moreover, we introduce the typical heterogeneous network representation learning techniques in detail and make a comparative analysis of these techniques. In addition, the research challenges in terms of semantics preserving, data sparsity and scalability are discussed. To tackle these challenges, several potential fu-ture research directions for heterogeneous network representation learning are pointed out, including semantic relations extraction, dynamic heterogeneous networks, very large heterogeneous networks and heterogeneous networks construction. (c) 2021 Elsevier Ltd. All rights reserved.