Representation Learning on Heterostructures via Heterogeneous Anonymous Walks
It addresses the challenge of capturing structural similarity in heterogeneous networks, which is important for understanding node functions and behaviors, but is incremental as it extends existing walk-based methods to heterogeneous contexts.
The paper tackles the problem of learning structural representations on heterogeneous networks, which was previously underexplored, by proposing heterogeneous anonymous walks and their embeddings, achieving outstanding performance compared to existing methods on synthetic and real-world networks.
Capturing structural similarity has been a hot topic in the field of network embedding recently due to its great help in understanding the node functions and behaviors. However, existing works have paid very much attention to learning structures on homogeneous networks while the related study on heterogeneous networks is still a void. In this paper, we try to take the first step for representation learning on heterostructures, which is very challenging due to their highly diverse combinations of node types and underlying structures. To effectively distinguish diverse heterostructures, we firstly propose a theoretically guaranteed technique called heterogeneous anonymous walk (HAW) and its variant coarse HAW (CHAW). Then, we devise the heterogeneous anonymous walk embedding (HAWE) and its variant coarse HAWE in a data-driven manner to circumvent using an extremely large number of possible walks and train embeddings by predicting occurring walks in the neighborhood of each node. Finally, we design and apply extensive and illustrative experiments on synthetic and real-world networks to build a benchmark on heterostructure learning and evaluate the effectiveness of our methods. The results demonstrate our methods achieve outstanding performance compared with both homogeneous and heterogeneous classic methods, and can be applied on large-scale networks.