Hyperbolic Graph Attention Network

Zhang, Yiding; Wang, Xiao; Shi, Chuan; Jiang, Xunqiang; Ye, Yanfang Fanny

doi:10.1109/tbdata.2021.3081431

Cited by 63 publications

(48 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some spatial methods focus on improving model capacity by introducing an attention mechanism to the graph domain, such as the Graph attention network (GAT), which adopts a self-attention mechanism to learn the weighting function [4]. Developments of GAT, such as Dual-primal graph convolutional network (DPGCN) [22] generalized GAT by using convolutions on nodes and edges, giving a better performance, Temporal graph attention network (TempGAN) learns node representations from continuous-time temporal graphs [23], and Hyperbolic graph attention network learns robust node representations of graphs in hyperbolic spaces [24]. The graph sample and aggregate method (GraphSage) [18], a nodebased spatial method, learns node, rather than graph, embeddings so it is graph-scale free and can be applied to large or evolving graphs.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Star Topology Convolution for Graph Representation Learning

Wang¹,

Feng²,

Zheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>We present a novel graph convolutional method called star topology convolution (STC). This method makes graph convolution more similar to conventional convolutional neural networks (CNNs) in Euclidean feature spaces. STC learns subgraphs which have a star topology rather than learning a fixed graph like most spectral methods. Due to the properties of a star topology, STC is graph-scale free (without a fixed graph size constraint). It has fewer parameters in its convolutional filter and is inductive, so it is more flexible and can be applied to large and evolving graphs. The convolutional filter is learnable and localized, similar to CNNs in Euclidean feature spaces, and maintains a good weight sharing property. To test the method, STC was compared with state-of-the-art graph convolutional methods in a supervised learning setting on nine node properties prediction benchmark datasets: Cora, Citeseer, Pubmed, PPI, Arxiv, MAG, ACM, DBLP, and IMDB. The experimental results showed that STC achieved state-of-the-art performance on all these datasets and maintained good robustness. In an essential protein identification task, STC outperformed state-of-the-art essential protein identification methods. Since the similarity between CNN and STC, some techniques of CNN can be applied in STC. We showed a study of introducing transfer learning in STC. The experimental results showed that transfer learning can be used to improve the performance of STC.<br></p>

show abstract

Section: Related Workmentioning

confidence: 99%

“…STC (conv only) or vanilla STC is based on Equation ( 16) to perform convolution only. STC-NARS is based on Equations (24)(25) to do graph representation learning on large heterogeneous graphs.…”

Section: Variantsmentioning

confidence: 99%

Star Topology Convolution for Graph Representation Learning

Wang¹,

Feng²,

Zheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Hyperbolic geometry has received increasing attention in machine learning and network science communities due to its attractive properties for modeling data with latent hierarchies. It has been applied to neural networks for problems of computer vision, natural language processing [16,29,30,32], and graph embedding tasks [6,16,24,40]. In the graph embedding field, recent works including HGNN [24], HGCN [6], and HGAT [40] generalize the graph convolution into hyperbolic space (the name of these methods are from corresponding literature) by moving the aggregation operation to the tangent space, where the vector operations can be performed.…”

Section: Related Workmentioning

confidence: 99%

“…It has been applied to neural networks for problems of computer vision, natural language processing [16,29,30,32], and graph embedding tasks [6,16,24,40]. In the graph embedding field, recent works including HGNN [24], HGCN [6], and HGAT [40] generalize the graph convolution into hyperbolic space (the name of these methods are from corresponding literature) by moving the aggregation operation to the tangent space, where the vector operations can be performed. HGNN [24] focuses more on graph classification tasks and provides an extension to dynamic graph embeddings.…”

Section: Related Workmentioning

confidence: 99%

“…This motivates us to rethink (1) whether the Euclidean manifold is the most suitable geometry for graph embedding of this kind of data and ( 2) is there any more powerful or proper alternative manifold to intrinsically preserve the graph properties, and if it exists, what benefits can it bring to temporal graph embedding? Recently, hyperbolic geometry has received increasing attention and achieves state-of-the-art performance in several static graph embedding tasks [6,24,29,30,40]. One fundamental property of hyperbolic space is that it expands exponentially and can be regarded as a smooth version of trees, abstracting the hierarchical organization [22].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space

Yang

Zhou

Kalander

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Representation learning over temporal networks has drawn considerable attention in recent years. Efforts are mainly focused on modeling structural dependencies and temporal evolving regularities in Euclidean space which, however, underestimates the inherent complex and hierarchical properties in many real-world temporal networks, leading to sub-optimal embeddings. To explore these properties of a complex temporal network, we propose a hyperbolic temporal graph network (HTGN) that fully takes advantage of the exponential capacity and hierarchical awareness of hyperbolic geometry. More specially, HTGN maps the temporal graph into hyperbolic space, and incorporates hyperbolic graph neural network and hyperbolic gated recurrent neural network, to capture the evolving behaviors and implicitly preserve hierarchical information simultaneously. Furthermore, in the hyperbolic space, we propose two important modules that enable HTGN to successfully model temporal networks: (1) hyperbolic temporal contextual self-attention (HTA) module to attend to historical states and (2) hyperbolic temporal consistency (HTC) module to ensure stability and generalization. Experimental results on multiple realworld datasets demonstrate the superiority of HTGN for temporal graph embedding, as it consistently outperforms competing methods by significant margins in various temporal link prediction tasks. Specifically, HTGN achieves AUC improvement up to 9.98% for link prediction and 11.4% for new link prediction. Moreover, the ablation study further validates the representational ability of hyperbolic geometry and the effectiveness of the proposed HTA and HTC modules. CCS CONCEPTS• Theory of computation → Dynamic graph algorithms; • Computing methodologies → Dimensionality reduction and manifold learning.

show abstract