DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation

TL;DR

DisenHAN introduces a novel disentangled heterogeneous graph attention network that improves top-N recommendation by explicitly modeling different semantic aspects in user-item interactions, leading to better performance and interpretability.

Contribution

The paper proposes a disentangled embedding propagation layer and meta relation decomposition to capture semantic aspects in heterogeneous graphs for recommendation.

Findings

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

The model provides interpretable disentangled representations.

Extensive experiments validate the effectiveness of the approach.

Abstract

Heterogeneous information network has been widely used to alleviate sparsity and cold start problems in recommender systems since it can model rich context information in user-item interactions. Graph neural network is able to encode this rich context information through propagation on the graph. However, existing heterogeneous graph neural networks neglect entanglement of the latent factors stemming from different aspects. Moreover, meta paths in existing approaches are simplified as connecting paths or side information between node pairs, overlooking the rich semantic information in the paths. In this paper, we propose a novel disentangled heterogeneous graph attention network DisenHAN for top-$N$ recommendation, which learns disentangled user/item representations from different aspects in a heterogeneous information network. In particular, we use meta relations to decompose high-order connectivity between node pairs and propose a disentangled embedding propagation layer which can iteratively identify the major aspect of meta relations. Our model aggregates corresponding aspect features from each meta relation for the target user/item. With different layers of embedding propagation, DisenHAN is able to explicitly capture the collaborative filtering effect semantically. Extensive experiments on three real-world datasets show that DisenHAN consistently outperforms state-of-the-art approaches. We further demonstrate the effectiveness and interpretability of the learned disentangled representations via insightful case studies and visualization.