Hypergraph neural networks. Feng, Y., You, H., Zhang, Z., Ji, R., & Gao, Y. 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, 2019. ![Hypergraph neural networks [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex In this paper, we present a hypergraph neural networks (HGNN) framework for data representation learning, which can encode high-order data correlation in a hypergraph struc ture. Confronting the challenges of learning representation for complex data in real practice, we propose to incorpo rate such data structure in a hypergraph, which is more flexi ble on data modeling, especially when dealing with complex data. In this method, a hyperedge convolution operation is designed to handle the data correlation during representation learning. In this way, traditional hypergraph learning proce dure can be conducted using hyperedge convolution opera tions efficiently. HGNN is able to learn the hidden layer rep resentation considering the high-order data structure, which is a general framework considering the complex data correla tions. We have conducted experiments on citation network classification and visual object recognition tasks and com pared HGNN with graph convolutional networks and other traditional methods. Experimental results demonstrate that the proposed HGNN method outperforms recent state-of-the-art methods. We can also reveal from the results that the pro posed HGNN is superior when dealing with multi-modal data compared with existing methods.
@article{
title = {Hypergraph neural networks},
type = {article},
year = {2019},
pages = {3558-3565},
id = {a942c4ca-9be3-3041-9787-ad006e039718},
created = {2021-09-02T06:33:40.755Z},
file_attached = {true},
profile_id = {ad172e55-c0e8-3aa4-8465-09fac4d5f5c8},
group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
last_modified = {2021-10-13T14:40:23.108Z},
read = {true},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
folder_uuids = {a6fefa10-ad39-4ee5-850c-dcbd4fed6307},
private_publication = {false},
abstract = {In this paper, we present a hypergraph neural networks (HGNN) framework for data representation learning, which can encode high-order data correlation in a hypergraph struc ture. Confronting the challenges of learning representation for complex data in real practice, we propose to incorpo rate such data structure in a hypergraph, which is more flexi ble on data modeling, especially when dealing with complex data. In this method, a hyperedge convolution operation is designed to handle the data correlation during representation learning. In this way, traditional hypergraph learning proce dure can be conducted using hyperedge convolution opera tions efficiently. HGNN is able to learn the hidden layer rep resentation considering the high-order data structure, which is a general framework considering the complex data correla tions. We have conducted experiments on citation network classification and visual object recognition tasks and com pared HGNN with graph convolutional networks and other traditional methods. Experimental results demonstrate that the proposed HGNN method outperforms recent state-of-the-art methods. We can also reveal from the results that the pro posed HGNN is superior when dealing with multi-modal data compared with existing methods.},
bibtype = {article},
author = {Feng, Yifan and You, Haoxuan and Zhang, Zizhao and Ji, Rongrong and Gao, Yue},
doi = {10.1609/aaai.v33i01.33013558},
journal = {33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019}
}
Downloads: 0
{"_id":"FGDBvAMfkyQTMjniF","bibbaseid":"feng-you-zhang-ji-gao-hypergraphneuralnetworks-2019","author_short":["Feng, Y.","You, H.","Zhang, Z.","Ji, R.","Gao, Y."],"bibdata":{"title":"Hypergraph neural networks","type":"article","year":"2019","pages":"3558-3565","id":"a942c4ca-9be3-3041-9787-ad006e039718","created":"2021-09-02T06:33:40.755Z","file_attached":"true","profile_id":"ad172e55-c0e8-3aa4-8465-09fac4d5f5c8","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2021-10-13T14:40:23.108Z","read":"true","starred":false,"authored":false,"confirmed":"true","hidden":false,"folder_uuids":"a6fefa10-ad39-4ee5-850c-dcbd4fed6307","private_publication":false,"abstract":"In this paper, we present a hypergraph neural networks (HGNN) framework for data representation learning, which can encode high-order data correlation in a hypergraph struc ture. Confronting the challenges of learning representation for complex data in real practice, we propose to incorpo rate such data structure in a hypergraph, which is more flexi ble on data modeling, especially when dealing with complex data. In this method, a hyperedge convolution operation is designed to handle the data correlation during representation learning. In this way, traditional hypergraph learning proce dure can be conducted using hyperedge convolution opera tions efficiently. HGNN is able to learn the hidden layer rep resentation considering the high-order data structure, which is a general framework considering the complex data correla tions. We have conducted experiments on citation network classification and visual object recognition tasks and com pared HGNN with graph convolutional networks and other traditional methods. Experimental results demonstrate that the proposed HGNN method outperforms recent state-of-the-art methods. We can also reveal from the results that the pro posed HGNN is superior when dealing with multi-modal data compared with existing methods.","bibtype":"article","author":"Feng, Yifan and You, Haoxuan and Zhang, Zizhao and Ji, Rongrong and Gao, Yue","doi":"10.1609/aaai.v33i01.33013558","journal":"33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019","bibtex":"@article{\n title = {Hypergraph neural networks},\n type = {article},\n year = {2019},\n pages = {3558-3565},\n id = {a942c4ca-9be3-3041-9787-ad006e039718},\n created = {2021-09-02T06:33:40.755Z},\n file_attached = {true},\n profile_id = {ad172e55-c0e8-3aa4-8465-09fac4d5f5c8},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2021-10-13T14:40:23.108Z},\n read = {true},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n folder_uuids = {a6fefa10-ad39-4ee5-850c-dcbd4fed6307},\n private_publication = {false},\n abstract = {In this paper, we present a hypergraph neural networks (HGNN) framework for data representation learning, which can encode high-order data correlation in a hypergraph struc ture. Confronting the challenges of learning representation for complex data in real practice, we propose to incorpo rate such data structure in a hypergraph, which is more flexi ble on data modeling, especially when dealing with complex data. In this method, a hyperedge convolution operation is designed to handle the data correlation during representation learning. In this way, traditional hypergraph learning proce dure can be conducted using hyperedge convolution opera tions efficiently. HGNN is able to learn the hidden layer rep resentation considering the high-order data structure, which is a general framework considering the complex data correla tions. We have conducted experiments on citation network classification and visual object recognition tasks and com pared HGNN with graph convolutional networks and other traditional methods. Experimental results demonstrate that the proposed HGNN method outperforms recent state-of-the-art methods. We can also reveal from the results that the pro posed HGNN is superior when dealing with multi-modal data compared with existing methods.},\n bibtype = {article},\n author = {Feng, Yifan and You, Haoxuan and Zhang, Zizhao and Ji, Rongrong and Gao, Yue},\n doi = {10.1609/aaai.v33i01.33013558},\n journal = {33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019}\n}","author_short":["Feng, Y.","You, H.","Zhang, Z.","Ji, R.","Gao, Y."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/02d3e9a8-0e3e-b3ff-4916-68aed5630c12/4235_Article_Text_7289_1_10_20190705.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"feng-you-zhang-ji-gao-hypergraphneuralnetworks-2019","role":"author","metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["6yXn8CtuzyEbCSr2m","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["hypergraph","neural","networks","feng","you","zhang","ji","gao"],"title":"Hypergraph neural networks","year":2019}