HAHE: Hierarchical Attentive Heterogeneous Information Network Embedding

TL;DR

The paper introduces HAHE, a hierarchical attention model for HIN embedding that captures personalized preferences on meta paths and path instances, improving performance on data mining tasks.

Contribution

It proposes a novel hierarchical attention mechanism to model personalized preferences in HIN embedding, addressing limitations of previous methods.

Findings

HAHE outperforms state-of-the-art methods on real-world datasets.

Hierarchical attention effectively captures personalized preferences.

Model improves results in various data mining tasks.

Abstract

Heterogeneous information network (HIN) embedding has recently attracted much attention due to its effectiveness in dealing with the complex heterogeneous data. Meta path, which connects different object types with various semantic meanings, is widely used by existing HIN embedding works. However, several challenges have not been addressed so far. First, different meta paths convey different semantic meanings, while existing works assume that all nodes share same weights for meta paths and ignore the personalized preferences of different nodes on different meta paths. Second, given a meta path, nodes in HIN are connected by path instances while existing works fail to fully explore the differences between path instances that reflect nodes' preferences in the semantic space. rTo tackle the above challenges, we propose aHierarchical Attentive Heterogeneous information network Embedding (HAHE) model to capture the personalized preferences on meta paths and path instances in each semantic space. As path instances are based on a particular meta path, a hierarchical attention mechanism is naturally utilized to model the personalized preference on meta paths and path instances. Extensive experiments on several real-world datasets show that our proposed \model model significantly outperforms the state-of-the-art methods in terms of various data mining tasks.