HAHE: Hierarchical Attentive Heterogeneous Information Network Embedding
arXiv:1902.01475
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.
References in corpus (10)
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Hierarchical Graph Representation Learning with Differentiable Pooling
- Attributed Network Embedding for Learning in a Dynamic Environment
- Attention-based Graph Neural Network for Semi-supervised Learning
- Watch Your Step: Learning Node Embeddings via Graph Attention
- Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks
- Heterogeneous Information Network Embedding for Meta Path based Proximity
- Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network
- Heterogeneous Information Network Embedding for Recommendation