English

Tensorized Hypergraph Neural Networks

Artificial Intelligence 2024-01-11 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2306.02560,
  title  = {Tensorized Hypergraph Neural Networks},
  author = {Maolin Wang and Yaoming Zhen and Yu Pan and Yao Zhao and Chenyi Zhuang and Zenglin Xu and Ruocheng Guo and Xiangyu Zhao},
  journal= {arXiv preprint arXiv:2306.02560},
  year   = {2024}
}

Comments

SIAM International Conference on Data Mining (SDM24)