Directed Hypergraph Representation Learning for Link Prediction

Zitong Ma, Wenbo Zhao, Zhe Yang
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:3268-3276, 2024.

Abstract

Link prediction is a critical problem in network structure processing. With the prevalence of deep learning, graph-based learning pattern in link prediction has been well-proven to successfully apply. However, existing representation-based computing paradigms retain some lack in processing complex networks: most methods only consider low-order pairwise information or eliminate the direction message, which tends to obtain a sub-optimal representation. To tackle the above challenges, we propose using directed hypergraph to model the real world and design a directed hypergraph neural network framework for data representation learning. Specifically, our work can be concluded into two sophisticated aspects: (1) We define the approximate Laplacian of the directed hypergraph, and further formulate the convolution operation on the directed hypergraph structure, solving the issue of the directed hypergraph structure representation learning. (2) By efficiently learning complex information from directed hypergraphs to obtain high-quality representations, we develop a framework DHGNN for link prediction on directed hypergraph structures. We empirically show that the merit of DHGNN lies in its ability to model complex correlations and encode information effectively of directed hypergraphs. Extensive experiments conducted on multi-field datasets demonstrate the superiority of the proposed DHGNN over various state-of-the-art approaches.

Cite this Paper


BibTeX
@InProceedings{pmlr-v238-ma24b, title = {Directed Hypergraph Representation Learning for Link Prediction}, author = {Ma, Zitong and Zhao, Wenbo and Yang, Zhe}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {3268--3276}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/ma24b/ma24b.pdf}, url = {https://proceedings.mlr.press/v238/ma24b.html}, abstract = {Link prediction is a critical problem in network structure processing. With the prevalence of deep learning, graph-based learning pattern in link prediction has been well-proven to successfully apply. However, existing representation-based computing paradigms retain some lack in processing complex networks: most methods only consider low-order pairwise information or eliminate the direction message, which tends to obtain a sub-optimal representation. To tackle the above challenges, we propose using directed hypergraph to model the real world and design a directed hypergraph neural network framework for data representation learning. Specifically, our work can be concluded into two sophisticated aspects: (1) We define the approximate Laplacian of the directed hypergraph, and further formulate the convolution operation on the directed hypergraph structure, solving the issue of the directed hypergraph structure representation learning. (2) By efficiently learning complex information from directed hypergraphs to obtain high-quality representations, we develop a framework DHGNN for link prediction on directed hypergraph structures. We empirically show that the merit of DHGNN lies in its ability to model complex correlations and encode information effectively of directed hypergraphs. Extensive experiments conducted on multi-field datasets demonstrate the superiority of the proposed DHGNN over various state-of-the-art approaches.} }
Endnote
%0 Conference Paper %T Directed Hypergraph Representation Learning for Link Prediction %A Zitong Ma %A Wenbo Zhao %A Zhe Yang %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-ma24b %I PMLR %P 3268--3276 %U https://proceedings.mlr.press/v238/ma24b.html %V 238 %X Link prediction is a critical problem in network structure processing. With the prevalence of deep learning, graph-based learning pattern in link prediction has been well-proven to successfully apply. However, existing representation-based computing paradigms retain some lack in processing complex networks: most methods only consider low-order pairwise information or eliminate the direction message, which tends to obtain a sub-optimal representation. To tackle the above challenges, we propose using directed hypergraph to model the real world and design a directed hypergraph neural network framework for data representation learning. Specifically, our work can be concluded into two sophisticated aspects: (1) We define the approximate Laplacian of the directed hypergraph, and further formulate the convolution operation on the directed hypergraph structure, solving the issue of the directed hypergraph structure representation learning. (2) By efficiently learning complex information from directed hypergraphs to obtain high-quality representations, we develop a framework DHGNN for link prediction on directed hypergraph structures. We empirically show that the merit of DHGNN lies in its ability to model complex correlations and encode information effectively of directed hypergraphs. Extensive experiments conducted on multi-field datasets demonstrate the superiority of the proposed DHGNN over various state-of-the-art approaches.
APA
Ma, Z., Zhao, W. & Yang, Z.. (2024). Directed Hypergraph Representation Learning for Link Prediction. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:3268-3276 Available from https://proceedings.mlr.press/v238/ma24b.html.

Related Material