.png){kind=icon}
.png){kind=icon}
Return
Sparse norm regularized attribute selection for graph neural networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.109265.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph Neural Networks (GNNs) have been widely used for graph learning tasks. The main aspect of GNN's layer-wise message passing is conducting attribute/feature propagation on graph. Most existing GNNs generally conduct feature propagation across all feature dimensions. However, in many real applications, attributes usually contain irrelevant and redundant noise. In this case, attribute/feature selection is de-sired to extract meaningful features and eliminate noisy ones for GNN's layer-wise propagation. Based on this observation, in this paper, we combine I; 2 , 1 /I; 1-norm regularized attribute selection and GNNs together and propose a novel Attribute selection guided GNNs (AsGNNs) for graph data representation. AsGNNs aim to adaptively select some desired meaningful features/attributes that best serve GNNs. More-over, an effective optimization framework has also been derived to train the proposed AsGNNs. The pro-posed AsGNNs provide a general framework which can incorporate any GNNs to conduct feature selection for layer-wise propagation. In this paper, we implement AsGNNs on both graph convolutional network (GCN) and graph attention network (GAT) and develop AsGCN and AsGAT for graph learning. Experimen-tal results on several benchmark datasets demonstrate the effectiveness of the proposed AsGNNs (AsGCN, AsGAT) on semi-supervised learning tasks.(c) 2022 Elsevier Ltd. All rights reserved.
Keywords:
Graph neural networks
Feature selection
Sparse regularization
Semi -supervised learning