Graph pooling via Dual-view Multi-level Infomax

Zhao, Qingqing; Zhang, Han; He, Mengyao; Li, Wei; Kang, Chuanze; Han, Mingjing

doi:10.1016/j.knosys.2022.110089

Cited by 7 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Downsampling, or pooling, avoids problems such as model overfitting is somewhat similar to the readout mechanism used to generate graphlevel representations [10]. Many researchers have proposed corresponding pooling methods based on ideas such as attention mechanism [27], ranking node importance [28], dual-view learning and fusion [29], and node merging [30].…”

Section: A Gnnsmentioning

confidence: 99%

Multi-Level Graph Neural Network With Sparsity Pooling for Recognizing Parkinson’s Disease

Zhang,

Zhou,

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Parkinson's disease (PD) is a neurodegenerative disease of the brain associated with motor symptoms. With the maturation of machine learning (ML), especially deep learning, ML has been used to assist in the diagnosis of PD. In this paper, we explore graph neural networks (GNNs) to implement PD prediction using MRI data. However, most existing GNN models suffer from the efficiency of graph construction on MRI data and the problem of overfitting on small data. This paper proposes a novel multi-layer GNN model that incorporates a fast graph construction method and a sparsitybased pooling layer with an attention mechanism. In addition, graph structure sparsity is plugged into the graph pooling layer as prior knowledge to mitigate overfitting in model training. Experimental results on real-world datasets demonstrate the effectiveness of the proposed model and its superiority over baseline methods.

show abstract