.png){kind=icon}
Return
Hypergraph Convolution on Nodes-Hyperedges Network for Semi-Supervised Node Classification
.png){kind=icon}
PRE
AI
DOI：10.1145/3494567.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Hypergraphs have shown great power in representing high-order relations among entities, and lots of hypergraph-based deep learning methods have been proposed to learn informative data representations for the node classification problem. However, most of these deep learning approaches do not take full consideration of either the hyperedge information or the original relationships among nodes and hyperedges. In this article, we present a simple yet effective semi-supervised node classification method named Hypergraph Convolution on Nodes-Hyperedges network, which performs filtering on both nodes and hyperedges as well as recovers the original hypergraph with the least information loss. Instead of only reducing the cross-entropy loss over the labeled samples as most previous approaches do, we additionally consider the hypergraph reconstruction loss as prior information to improve prediction accuracy. As a result, by taking both the crossentropy loss on the labeled samples and the hypergraph reconstruction loss into consideration, we are able to achieve discriminative latent data representations for training a classifier. We perform extensive experiments on the semi-supervised node classification problem and compare the proposed method with state-of-the-art algorithms. The promising results demonstrate the effectiveness of the proposed method.
Keywords:
Hypergraph
hypergraph auto-encoder
hypergraph convolution
node classification
Journal
IF:
4.8
Papers:
1.3K
Citations:
4.4K
Organization
Cited Papers
Catabolite inactivation of fructose‐1,6‐bisphosphatase in yeast is mediated by the proteasome.png)
FEBS Letters
OAAI
FEBS LettersIF0
OAAIShareSaveShareSavePassive signal propagation and membrane properties in median photoreceptors of the giant barnacleOAAI
OAAIShareSaveEfficacy of Brivaracetam (BRV) as Adjunctive Therapy in Partial-Onset (Focal) Seizures Among Patients with Prior Levetiracetam (LEV), Carbamazepine (CBZ), Lamotrigine (LTG), or Topiramate (TPM) Exposure (P2.027)Neurology
NeurologyIF0
PREAI
ShareSaveShareSave
View more