Results 71 to 80 of about 665 (142)

Scientific Paper Classification Based on Graph Neural Network with Hypergraph Self-attention Mechanism

, 2022
The number of scientific papers has increased rapidly in recent years. How to make good use of scientific papers for research is very important. Through the high-quality classification of scientific papers, researchers can quickly find the resource ...
Li, Ang, Liu, Jiashun, Xue, Zhe
core  

Hypergraph Self-supervised Learning with Sampling-efficient Signals [PDF]

Self-supervised learning (SSL) provides a promising alternative for representation learning on hypergraphs without costly labels. However, existing hypergraph SSL models are mostly based on contrastive methods with the instance-level discrimination ...
Li, Fan, Zhang, Wenjie, Zhang, Ying, Cheng, Dawei, Wang, Xiaoyang, Lin, Xuemin   +5 more
core   +1 more source

A note on self-complementary hypergraphs

Tyt. z nagł.Abstract. In the paper we desribe all self-complementary hypergraphs. It turns out that such hypergraphs exist if and only if the number of vertices of the hypergraph is of the form n = 2k. This answers a conjecture posed by A. Szymański (see
Zwonek, Małgorzata.
core  

A note on self-complementary 4-uniform hypergraphs

Tyt. z nagł.Abstract. We prove that a permutation theta is complementing permutation for a 4-uniform hypergraph if and only if one of the following cases is satisfied: (i) the length of every cycle of theta is a multiple of 8, (ii) theta has 1, 2 or 3 ...
Szymański, Artur
core  

FedMSGL: A Self-Expressive Hypergraph Based Federated Multi-View Learning

Federated learning is essential for enabling collaborative model training across decentralized data sources while preserving data privacy and security. This approach mitigates the risks associated with centralized data collection and addresses concerns ...
Yang, Zuyuan, Li, Daoyuan, Xie, Shengli
core   +1 more source

CHGNN:A Semi-Supervised Contrastive Hypergraph Learning Network.

Hypergraphs can model higher-order relationships among data objects that are found in applications such as social networks and bioinformatics. However, recent studies on hypergraph learning that extend graph convolutional networks to hypergraphs cannot ...
Song, Yumeng, Gu, Yu, Li, Tianyi, Qi, Jianzhong, Jensen, Christian S.; id_orcid, Yu, Ge, Liu, Zhenghao   +6 more
core   +1 more source

Traffic flow prediction via dynamic hypergraph learning. [PDF]

PLoS One
Wei S, Yang Y, Wang C.
europepmc   +1 more source

DHGCMDA: a dual-view heterogeneous graph contrastive learning framework for miRNA-disease association type prediction. [PDF]

BMC Bioinformatics
Sun Y, Zhang F, Yan S, Kong X, Wang H, Shang J, Liu JX.   +6 more
europepmc   +1 more source

HYG-mol: An Interpretable Multimodal Hypergraph Framework for Molecular Property Prediction. [PDF]

Comput Struct Biotechnol J
Ma J, Yang Q, Zhang L, Liu H, Zheng Y.
europepmc   +1 more source

Inferring gene regulatory networks by hypergraph generative model

Summary: We present hypergraph variational autoencoder (HyperG-VAE), a Bayesian deep generative model that leverages hypergraph representation to model single-cell RNA sequencing (scRNA-seq) data.
Hanchen Wang, Marc R. Wilkins, Ying Zhang, Di Yu, Yang Yang, Pablo F. Canete, Wenjie Zhang, Guangxin Su   +7 more
core   +1 more source