HNHN: Hypergraph Networks with Hyperedge Neurons

Abstract

Hypergraphs provide a natural representation for many real world datasets. We propose a novel framework, HNHN, for hypergraph representation learning. HNHN is a hypergraph convolution network with nonlinear activation functions applied to both hypernodes and hyperedges, combined with a normalization scheme that can flexibly adjust the importance of high-cardinality hyperedges and high-degree vertices depending on the dataset. We demonstrate improved performance of HNHN in both classification accuracy and speed on real world datasets when compared to state of the art methods.

References in corpus (1)

• Hyper-SAGNN: a self-attention based graph neural network for hypergraphs

Cited by in corpus (4)

• Principled Hyperedge Prediction with Structural Spectral Features and Neural Networks
• DecGAN: Decoupling Generative Adversarial Network detecting abnormal neural circuits for Alzheimer's disease
• Adaptive Neural Message Passing for Inductive Learning on Hypergraphs
• Characterization Multimodal Connectivity of Brain Network by Hypergraph GAN for Alzheimer's Disease Analysis