Graph neural network (GNN) has shown superior performance in dealing with graphs, which has attracted considerable research attention recently. However, most of the existing GNN models are primarily designed for graphs in Euclidean spaces. Recent research has proven that the graph data exhibits non-...
(2) We introduce a hyperbolic attention-based aggregation scheme that captures node hierarchies. (3) We apply feature transformations in hyperbolic spaces of different trainable curvatures at different layers, to learn hyperbolic embeddings that preserve the graph structure and a notion of hierarchy for...
Citeseer20.2570.3160.1930.1800.2870.3570.5120.546 40.4010.4270.2260.2430.3100.5560.6560.681 80.4270.4510.2610.2450.3650.6790.6970.712 160.4590.4710.3070.2690.3990.7040.7040.719 Pubmed20.5350.5650.3420.3790.6140.6320.7430.761 40.6450.6690.5040.3800.6290.7080.7610.767 ...
Knowledge graphGraph convolutional networkLink predictionGraph convolutional networks (GCNs) have received widespread attention in the field of knowledge graph embedding (KGE) due to their powerful graph modeling and neighbor information aggregation capabilities. The GCNs-based embedding methods typically use ...
(or None for no activation) --n-heads N_HEADS number of attention heads for graph attention networks, must be a divisor dim --alpha ALPHA alpha for leakyrelu in graph attention networks --use-att USE_ATT whether to use hyperbolic attention in HGCN model --double-precision DOUBLE_PRECISION...
The main contributions of our work are as follows: • We are the first to address hand-object reconstruction in hyperbolic space, proposing a novel Dynamic Hy- perbolic Attention Network. • We devise a Dynamic Hyperbolic Graph Convolution to dynamically learn ...
The proposed Graph Learning with Label Attention (GLLA) model offers significant advancements in temporal event prediction in healthcare. By integrating label attention, hyperbolic embeddings, and collaborative graph learning, GLLA addresses several limitations of existing approaches and demonstrates superior...
A Hyperbolic-to-Hyperbolic Graph Convolutional Network, CVPR 2021 Jindou Dai, Yuwei Wu, Zhi Gao, Yunde Jia Hyperbolic Graph Attention Network, Transcations on Big Data 2021 Yiding Zhang, Xiao Wang, Xunqiang Jiang, Chuan Shi, Yanfang Ye Unsupervised Hyperbolic Representation Learning via Message...
Hyperbolic hierarchical graph attention network for knowledge graph completion Utilizing graph neural networks for knowledge embedding to accomplish the task of knowledge graph completion(KGC) has become an important research area in ... 许浩,CHEN Shudong,QI Donglin,... - 《High Technology Letters》...
To capture the scale-free spatial and temporal dependencies in stock prices, we propose HyperStockGAT: Hyperbolic Stock Graph Attention Network, the first model on the Riemannian Manifolds for stock selection. Our work's key novelty is the proposal of modeling the complex, scale-free nature of ...