Filters








598 Hits in 3.2 sec

Heterogeneous Hypergraph Embedding for Graph Classification [article]

Xiangguo Sun, Hongzhi Yin, Bo Liu, Hongxu Chen, Jiuxin Cao, Yingxia Shao, Nguyen Quoc Viet Hung
2021 arXiv   pre-print
In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise  ...  Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning.  ...  (Heterogenous Hypergraph Embedding for Graph Classification).  ... 
arXiv:2010.10728v3 fatcat:wrfvahvqsbgwnmeovxe4u5qtai

Heterogeneous Hypergraph Embedding for Graph Classification

Xiangguo Sun, Hongzhi Yin, Bo Liu, Hongxu Chen, Jiuxin Cao, Yingxia Shao, Nguyen Quoc Viet Hung
2021 Proceedings of the 14th ACM International Conference on Web Search and Data Mining  
In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise  ...  Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning.  ...  (Heterogenous Hypergraph Embedding for Graph Classification).  ... 
doi:10.1145/3437963.3441835 fatcat:mxqbdztybnhghmtqykv6zgpav4

Graph Neural Networks Designed for Different Graph Types: A Survey [article]

Josephine M. Thomas and Alice Moallemy-Oureh and Silvia Beddar-Wiesing and Clara Holzhüter
2022 arXiv   pre-print
Graphs are ubiquitous in nature and can therefore serve as models for many practical but also theoretical problems.  ...  We point out where models are missing and give potential reasons for their absence.  ...  Acknowledgment The GAIN-project is funded by the Ministry of Education and Research Germany (BMBF), under the funding code 01IS20047A, according to the 'Policy for the funding of female junior researchers  ... 
arXiv:2204.03080v2 fatcat:52o4dx5ulve3na7vndmbpqhpcm

Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks [article]

Hansheng Xue and Luwei Yang and Vaibhav Rajan and Wen Jiang and Yi Wei and Yu Lin
2021 arXiv   pre-print
A large number of network embedding methods exist to learn vectorial node representations from general graphs with both homogeneous and heterogeneous node and edge types, including some that can specifically  ...  spectral hypergraph convolutional operators, along with intra- and inter-message passing strategies to promote information exchange within and across domains, to learn effective node embedding.  ...  MGCN [5] considers both local and hypergraph level graph convolutions and is able to capture wider and richer network information for network embedding.  ... 
arXiv:2102.06371v1 fatcat:xwcsxbvhpzdczbwivzowr6xira

Deep Hypergraph U-Net for Brain Graph Embedding and Classification [article]

Mert Lostar, Islem Rekik
2020 arXiv   pre-print
Graph embedding methods which map data samples (e.g., brain networks) into a low dimensional space have been widely used to explore the relationship between samples for classification or prediction tasks  ...  Our HUNet outperformed state-of-the-art geometric graph and hypergraph data embedding techniques with a gain of 4-14% in classification accuracy, demonstrating both scalability and generalizability.  ...  In this paper we propose the Hypergraph U-Net (HUNet) architecture for high-order data embedding by generalizing the graph U-Net to hypergraphs.  ... 
arXiv:2008.13118v1 fatcat:xkyg5ddmzbg6fktxwqcmqfttoi

Hyper-SAGNN: a self-attention based graph neural network for hypergraphs [article]

Ruochi Zhang, Yuesong Zou, Jian Ma
2019 arXiv   pre-print
Here we develop a new self-attention based graph neural network called Hyper-SAGNN applicable to homogeneous and heterogeneous hypergraphs with variable hyperedge sizes.  ...  Graph representation learning for hypergraphs can be used to extract patterns among higher-order interactions that are critically important in many real world problems.  ...  to predict hyperedges for non-k-uniform heterogeneous hypergraphs.  ... 
arXiv:1911.02613v1 fatcat:ktalcl2hfnhuvkwjydbtmmqou4

Semi-supervised hypergraph discriminant learning for hyperspectral image classification

Fulin Luo, Tan Guo, Zhiping Lin, Jinchang Ren, Xiaocheng Zhou
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
by designing an intraclass hypergraph and an interclass graph with the labeled samples.  ...  Index Terms-Dimensionality reduction (DR), graph learning, hyperspectral image (HSI) classification, locality-constrained linear coding, neighborhood margin.  ...  ACKNOWLEDGMENT The authors would like to thank the handling editor and the anonymous reviewers for their detailed and constructive comments and suggestions, which indeed helped to improve the quality of  ... 
doi:10.1109/jstars.2020.3011431 fatcat:qa3iau3u2zeshnvewv47ddm5vi

Hypergraph and Uncertain Hypergraph Representation Learning Theory and Methods

Liyan Zhang, Jingfeng Guo, Jiazheng Wang, Jing Wang, Shanshan Li, Chunying Zhang
2022 Mathematics  
learning methods of ordinary graphs and hypergraphs from three aspects: matrix decomposition, random walk, and deep learning; next, introduced the structural optimization of hypergraphs from three perspectives  ...  : dynamic hypergraphs, hyperedge weight optimization, and multimodal hypergraph generation; after that, the applicability of three uncertain hypergraph models were analyzed based on three uncertainty theories  ...  GCN does the same thing as CNN, extracting graph structure features for graph data and using them for node classification, graph classification, edge prediction, graph representation learning, etc.  ... 
doi:10.3390/math10111921 fatcat:rg75472l5vetph7lfcfrys3jty

Be More with Less: Hypergraph Attention Networks for Inductive Text Classification [article]

Kaize Ding, Jianling Wang, Jundong Li, Dingcheng Li, Huan Liu
2020 arXiv   pre-print
To address those issues, in this paper, we propose a principled model -- hypergraph attention networks (HyperGAT), which can obtain more expressive power with less computational consumption for text representation  ...  Text classification is a critical research topic with broad applications in natural language processing.  ...  Figure 1 : 1 Illustration of the proposed hypergraph attention networks (HyperGAT) for inductive text classification. We construct a hypergraph for each text document and feed it into HyperGAT.  ... 
arXiv:2011.00387v1 fatcat:jvvct7zx4vb6xbwnwljn3trvlq

Lovasz Convolutional Networks [article]

Prateek Yadav, Madhav Nimishakavi, Naganand Yadati, Shikhar Vashishth, Arun Rajkumar, Partha Talukdar
2019 arXiv   pre-print
We validate the proposed method on standard random graph models such as stochastic block models (SBM) and certain community structure based graphs where LCNs outperform GCNs and learn more intuitive embeddings  ...  We also perform extensive binary and multi-class classification experiments on real world datasets to demonstrate LCN's effectiveness.  ...  Hypergraphs: Homogeneous vs Heterogeneous Edges Experiment: Though our main focus is on simple graphs, we also experiment with synthetic hypergraphs.  ... 
arXiv:1805.11365v3 fatcat:i3zjynz6b5ffpelcrbz6uwdq3y

Hypergraph Convolution and Hypergraph Attention [article]

Song Bai, Feihu Zhang, Philip H.S. Torr
2020 arXiv   pre-print
To efficiently learn deep embeddings on the high-order graph-structured data, we introduce two end-to-end trainable operators to the family of graph neural networks, i.e., hypergraph convolution and hypergraph  ...  Extensive experimental results with semi-supervised node classification demonstrate the effectiveness of hypergraph convolution and hypergraph attention.  ...  Graph Neural Network (GNN) is a methodology for learning deep models or embeddings on graph-structured data, which was first proposed by [5] .  ... 
arXiv:1901.08150v2 fatcat:gqanvg6tqrhchlx2dlub5iosgu

Transductive Multi-View Zero-Shot Learning

Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Shaogang Gong
2015 IEEE Transactions on Pattern Analysis and Machine Intelligence  
To overcome this problem, a novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space.  ...  We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding, to solve it.  ...  heterogeneous hypergraph is more effective than the homogeneous 2-graphs used in TMV-BLP for zero-shot learning.  ... 
doi:10.1109/tpami.2015.2408354 pmid:26440271 fatcat:eazqbmoc6vholji7ke6yyis5wq

Multi-View Brain HyperConnectome AutoEncoder For Brain State Classification [article]

Alin Banka, Inis Buzi, Islem Rekik
2020 arXiv   pre-print
Graph embedding is a powerful method to represent graph neurological data (e.g., brain connectomes) in a low dimensional space for brain connectivity mapping, prediction and classification.  ...  Second, existing graph embedding techniques cannot be easily adapted to multi-view graph data with heterogeneous distributions.  ...  It utilizes conventional graph convolutional layers to learn the embeddings and adversarial regularizing network for original-encoded distribution alignment.  ... 
arXiv:2009.11553v1 fatcat:pkdsaihiqrarvfjs4wep3wdw3m

Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph Embedding

Hong Huang, Meili Chen, Yule Duan
2019 Remote Sensing  
A new DR method termed spatial-spectral regularized sparse hypergraph embedding (SSRHE) is proposed for the HSI classification.  ...  Many graph embedding methods are developed for dimensionality reduction (DR) of hyperspectral image (HSI), which only use spectral features to reflect a point-to-point intrinsic relation and ignore complex  ...  Acknowledgments: The authors would like to thank the anonymous reviewers and associate editor for their valuable comments and suggestions to improve the quality of the paper.  ... 
doi:10.3390/rs11091039 fatcat:bzytghbvlredpdwqhd7fmrp3zm

DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks [article]

Mubashir Imran, Hongzhi Yin, Tong Chen, Zi Huang, Kai Zheng
2022 arXiv   pre-print
link prediction and node classification.  ...  Such heterogeneous network embedding (HNE) methods effectively harness the heterogeneity of small-scale HINs.  ...  Specifically, our work is relevant to heterogeneous network embedding, large-scale network embedding and hypergraph embedding.  ... 
arXiv:2201.02757v1 fatcat:zv3hsqo4drcr5m7cm3v2kaua34
« Previous Showing results 1 — 15 out of 598 results