Tensorized Hypergraph Neural Networks Article Swipe

MAKE IMPACT

Maolin Wang , Yaoming Zhen , Pan Yu , Zenglin Xu , Ruocheng Guo , Xiangyu Zhao · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2306.02560

Hypergraph neural networks (HGNN) have recently become attractive and received significant attention due to their excellent performance in various domains. However, most existing HGNNs rely on first-order approximations of hypergraph connectivity patterns, which ignores important high-order information. To address this issue, we propose a novel adjacency-tensor-based \textbf{T}ensorized \textbf{H}ypergraph \textbf{N}eural \textbf{N}etwork (THNN). THNN is a faithful hypergraph modeling framework through high-order outer product feature message passing and is a natural tensor extension of the adjacency-matrix-based graph neural networks. The proposed THNN is equivalent to a high-order polynomial regression scheme, which enables THNN with the ability to efficiently extract high-order information from uniform hypergraphs. Moreover, in consideration of the exponential complexity of directly processing high-order outer product features, we propose using a partially symmetric CP decomposition approach to reduce model complexity to a linear degree. Additionally, we propose two simple yet effective extensions of our method for non-uniform hypergraphs commonly found in real-world applications. Results from experiments on two widely used {hypergraph datasets for 3-D visual object classification} show the model's promising performance.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2306.02560

PDF

https://arxiv.org/pdf/2306.02560

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4379539678

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4379539678

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2306.02560

Digital Object Identifier

Title

Tensorized Hypergraph Neural Networks

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-06-05

Full publication date if available

Authors

Maolin Wang, Yaoming Zhen, Pan Yu, Zenglin Xu, Ruocheng Guo, Xiangyu Zhao

List of authors in order

Landing page

https://arxiv.org/abs/2306.02560

Publisher landing page

PDF URL

https://arxiv.org/pdf/2306.02560

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2306.02560

Direct OA link when available

Concepts

Hypergraph, Adjacency list, Adjacency matrix, Artificial neural network, Computer science, Order (exchange), Polynomial, Simple (philosophy), Graph, Theoretical computer science, Mathematics, Discrete mathematics, Algorithm, Artificial intelligence, Finance, Epistemology, Economics, Mathematical analysis, Philosophy

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload