Semi-Supervised Classification via Hypergraph Convolutional Extreme Learning Machine

Applied Sciences

Zhikun Chen¹  Zhewei Liu²  Yaoming Cai²  Zijia Zhang²  Yilin Miao² 

[1] Guangxi Key Laboratory of Marine Disaster in the Beibu Gulf, Beibu Gulf University, Qinzhou 535011, China;School of Computer Science, China University of Geosciences, Wuhan 430078, China;

关键词: graph convolutional network;    extreme learning machine;    semi-supervised learning;    hypergraph learning;   

DOI  :  10.3390/app11093867

来源: DOAJ

【 摘 要 】

Extreme Learning Machine (ELM) is characterized by simplicity, generalization ability, and computational efficiency. However, previous ELMs fail to consider the inherent high-order relationship among data points, resulting in being powerless on structured data and poor robustness on noise data. This paper presents a novel semi-supervised ELM, termed Hypergraph Convolutional ELM (HGCELM), based on using hypergraph convolution to extend ELM into the non-Euclidean domain. The method inherits all the advantages from ELM, and consists of a random hypergraph convolutional layer followed by a hypergraph convolutional regression layer, enabling it to model complex intraclass variations. We show that the traditional ELM is a special case of the HGCELM model in the regular Euclidean domain. Extensive experimental results show that HGCELM remarkably outperforms eight competitive methods on 26 classification benchmarks.

【 授权许可】

Unknown