Representation Learning on Multi-layered Heterogeneous Network

Network data can often be represented in a multi-layered structure with rich semantics. One example is e-commerce data, containing user-user social network layer and item-item context layer, with cross-layer user-item interactions. Given the dual characters of homogeneity within each layer and heterogeneity across layers, we seek to learn node representations from such a multi-layered heterogeneous network while jointly preserving structural information and network semantics. In contrast, previous works on network embedding mainly focus on single-layered or homogeneous networks with one type of nodes and links. In this paper we propose intra- and cross-layer proximity concepts. Intra-layer proximity simulates propagation along homogeneous nodes to explore latent structural similarities. Cross-layer proximity captures network semantics by extending heterogeneous neighborhood across layers. Through extensive experiments on four datasets, we demonstrate that our model achieves substantial gains in different real-world domains over state-of-the-art baselines.