Heterogeneous Graph Attention Network

  title={Heterogeneous Graph Attention Network},
  author={Xiao Wang and Houye Ji and Chuan Shi and Bai Wang and Peng Cui and Pinggang Yu and Yanfang Ye},
  journal={The World Wide Web Conference},
Graph neural network, as a powerful graph representation technique based on deep learning, has shown superior performance and attracted considerable research interest. [] Key Method With the learned importance from both node-level and semantic-level attention, the importance of node and meta-path can be fully considered. Then the proposed model can generate node embedding by aggregating features from meta-path based neighbors in a hierarchical manner. Extensive experimental results on three real-world…

Figures and Tables from this paper

MBHAN: Motif-Based Heterogeneous Graph Attention Network

This paper presents a novel motif-based hierarchical heterogeneous graph attention network algorithm, MBHAN, that addresses this problem by incorporating a hierarchical dual attention mechanism at the node-level and motif-level.

LEHAN: Link-Feature Enhanced Heterogeneous Graph Attention Network

A Link-feature Enhanced Heterogeneous graph Attention Network (LEHAN) that focuses on the node and link features to represent heterogeneous graphs and outperforms the state-of-the-art graph embedding algorithms in node classification and clustering on real-world heterogeneous graph graphs.

SHGNN: Structure-Aware Heterogeneous Graph Neural Network

A novel Structure-Aware Heterogeneous Graph Neural Network (SHGNN) is proposed to address the above limitations and achieves state-of-the-art results on the benchmark datasets, which shows the effectiveness of the proposed method.

Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks

Experimental results not only show HAEGNN’s superior performance against the state-of-the-art methods in node classification, node clustering, and visualization, but also demonstrate its superiorities in terms of memory efficiency and explainability.

Heterogeneous Graph Propagation Network

This work proposes a novel Heterogeneous graph Propagation Network (HPN), which improves the node-level aggregating process via absorbing node’s local semantic with a proper weight, which makes HPN capture the characteristics of each node and learn distinguishable node embedding with deeper HeteGNN architecture.

WMGCN: Weighted Meta-Graph Based Graph Convolutional Networks for Representation Learning in Heterogeneous Networks

To fully capture the complex long semantic information, MGCN utilizes different meta-graphs in HNs, and improves the current convolution design by adding node self-significance.

Heterogeneous Deep Graph Infomax

An unsupervised graph neural network Heterogeneous Deep Graph Infomax (HDGI) for heterogeneous graph representation learning is proposed, which uses the meta-path structure to analyze the connections involving semantics in heterogeneous graphs and utilize graph convolution module and semantic-level attention mechanism to capture local representations.

An Attention-based Graph Neural Network for Heterogeneous Structural Learning

A novel Heterogeneous Graph Structural Attention Neural Network (HetSANN) is proposed to directly encode structural information of HIN without meta-path and achieve more informative representations.

Non-local Attention Learning on Large Heterogeneous Information Networks

This work proposes a novel framework of non-local attention in heterogeneous information networks (NLAH), which leverages both local and non- local information simultaneously and outperforms state-of-the-art baselines with significant margins.

Heterogeneous Graph Neural Network via Attribute Completion

It is held that missing attributes can be acquired by a learnable manner, and a general framework for Heterogeneous Graph Neural Network via Attribute Completion (HGNN-AC), including pre-learning of topological embedding and attribute completion with attention mechanism is proposed.



Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks

This work proposesMEta-GrAph-based network embedding models, called MEGA and MEGA++, respectively, which uses normalized relevance or similarity measures that are derived from a meta-graph and its embedded meta-paths between nodes simultaneously, and then leverages tensor decomposition method to perform node embedding.

metapath2vec: Scalable Representation Learning for Heterogeneous Networks

Two scalable representation learning models, namely metapath2vec and metapATH2vec++, are developed that are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, but also discern the structural and semantic correlations between diverse network objects.

Leveraging Meta-path based Context for Top- N Recommendation with A Neural Co-Attention Model

A novel deep neural network with the co-attention mechanism for leveraging rich meta-path based context for top-N recommendation and performs well in the cold-start scenario and has potentially good interpretability for the recommendation results.

HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning

Empirical results show that HIN2Vec soundly outperforms the state-of-the-art representation learning models for network data, including DeepWalk, LINE, node2vec, PTE, HINE and ESim, by 6.6% to 23.8% of $micro$-$f_1$ in multi-label node classification and 5% to 70.8%, in link prediction.

Gated Graph Sequence Neural Networks

This work studies feature learning techniques for graph-structured inputs and achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be matched to abstract data structures.

node2vec: Scalable Feature Learning for Networks

In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.

Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks

This paper re-examine similarity search in HINs and proposes a novel embedding-based framework, ESim, that accepts user-defined meta-paths as guidance to learn vertex vectors in a user-preferred embedding space to explore network structure-embedded similarity.

Structural Deep Network Embedding

This paper proposes a Structural Deep Network Embedding method, namely SDNE, which first proposes a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non- linear network structure and exploits the first-order and second-order proximity jointly to preserve the network structure.

Modeling Relational Data with Graph Convolutional Networks

It is shown that factorization models for link prediction such as DistMult can be significantly improved through the use of an R-GCN encoder model to accumulate evidence over multiple inference steps in the graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline.

Heterogeneous Information Network Embedding for Recommendation

A novel heterogeneous network embedding based approach for HIN based recommendation, called HERec is proposed, which shows the capability of the HERec model for the cold-start problem, and reveals that the transformed embedding information from HINs can improve the recommendation performance.