Heterogeneous Graph Attention Network

Wang, Xiao; Ji, Houye; Shi, Chuan; Bai, Wei; Ye, Yanfang; Cui, Peng; Yu, Philip S.

doi:10.1145/3308558.3313562

Cited by 1,636 publications

(1,027 citation statements)

References 26 publications

Supporting

Mentioning

1,010

Contrasting

Order By: Relevance

“…This module simply conducts different linear projections for nodes of different types. Such a procedure can be regarded to map heterogeneous data into the same distribution, which is also adopted in literature [23,27]. Implementation Details.…”

Section: Methodsmentioning

confidence: 99%

“…One of the classical paradigms is to define and use meta paths to model heterogeneous structures, such as PathSim [18] and metapath2vec [3]. Recently, in view of graph neural networks' (GNNs) success [7,9,22], there are several attempts to adopt GNNs to learn with heterogeneous networks [14,23,26,27]. However, these works face several issues: First, most of them involve the design of meta paths for each type of heterogeneous graphs, requiring specific domain knowledge; Second, they either simply assume that different types of nodes/edges share the same feature and representation space or keep distinct non-sharing weights for either node type or edge type alone, making them insufficient to capture heterogeneous graphs' properties; Third, most of them ignore the dynamic nature of every (heterogeneous) graph; Finally, their intrinsic design and implementation make them incapable of modeling Web-scale heterogeneous graphs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Heterogeneous Graph Transformer

Dong

Wang

et al. 2020

Proceedings of the Web Conference 2020

674

483

View full text Add to dashboard Cite

Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them infeasible to represent heterogeneous structures. In this paper, we present the Heterogeneous Graph Transformer (HGT) architecture for modeling Web-scale heterogeneous graphs. To model heterogeneity, we design node-and edge-type dependent parameters to characterize the heterogeneous attention over each edge, empowering HGT to maintain dedicated representations for different types of nodes and edges. To handle dynamic heterogeneous graphs, we introduce the relative temporal encoding technique into HGT, which is able to capture the dynamic structural dependency with arbitrary durations. To handle Web-scale graph data, we design the heterogeneous mini-batch graph sampling algorithm-HGSampling-for efficient and scalable training. Extensive experiments on the Open Academic Graph of 179 million nodes and 2 billion edges show that the proposed HGT model consistently outperforms all the state-of-the-art GNN baselines by 9%-21% on various downstream tasks. The dataset and source code of HGT are publicly available at https://github.com/acbull/pyHGT.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Heterogeneous Graph Transformer

Dong

Wang

et al. 2020

Proceedings of the Web Conference 2020

674

483

View full text Add to dashboard Cite

show abstract

“…(2) The model discards all intermediate nodes along the metapath by only considering two end nodes, which results in information loss (e.g., HERec [23] and HAN [31]). (3) The model relies on a single metapath to embed the heterogeneous graph.…”

Section: Introductionmentioning

confidence: 99%

MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

Zhang

Meng

et al. 2020

Proceedings of the Web Conference 2020

496

343

View full text Add to dashboard Cite

A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types. Heterogeneous graph embedding is to embed rich structural and semantic information of a heterogeneous graph into low-dimensional node representations. Existing models usually define multiple metapaths in a heterogeneous graph to capture the composite relations and guide neighbor selection. However, these models either omit node content features, discard intermediate nodes along the metapath, or only consider one metapath. To address these three limitations, we propose a new model named Metapath Aggregated Graph Neural Network (MAGNN) to boost the final performance. Specifically, MAGNN employs three major components, i.e., the node content transformation to encapsulate input node attributes, the intra-metapath aggregation to incorporate intermediate semantic nodes, and the inter-metapath aggregation to combine messages from multiple metapaths. Extensive experiments on three real-world heterogeneous graph datasets for node classification, node clustering, and link prediction show that MAGNN achieves more accurate prediction results than state-of-the-art baselines.

show abstract

“…R. Hu and other side information [10], [11]. This new learning paradigm has shifted the tasks of seeking complex models for classification, clustering, and link prediction [12] to learning a compact and informative representation for the graph data, so that many graph mining tasks can be easily performed by employing simple traditional models (e.g., a linear SVM for the classification task).…”

Section: Introductionmentioning

confidence: 99%

Learning Graph Embedding With Adversarial Training Methods

Pan

Fung

et al. 2020

IEEE Trans. Cybern.

227

View full text Add to dashboard Cite

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes, which unfortunately may lead to inferior representation in many cases. In this paper, we present a novel adversarially regularized framework for graph embedding. By employing the graph convolutional network as an encoder, our framework embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph. The adversarial training principle is applied to enforce our latent codes to match a prior Gaussian or Uniform distribution. Based on this framework, we derive two variants of adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively. We also exploit other potential variations of ARGA and ARVGA to get a deeper understanding on our designs. Experimental results compared among twelve algorithms for link prediction and twenty algorithms for graph clustering validate our solutions.

show abstract

Heterogeneous Graph Attention Network

Cited by 1,636 publications

References 26 publications

Heterogeneous Graph Transformer

Heterogeneous Graph Transformer

MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

Learning Graph Embedding With Adversarial Training Methods

Contact Info

Product

Resources

About