Sparse norm regularized attribute selection for graph neural networks. (May 2023)

• Record Type: Journal Article
• Authors: Jiang, Bo; Wang, Beibei; Luo, Bin
• Is Part Of: Pattern recognition. Volume 137(2023)
• Publication Date: 2023-05
• Subjects: Graph neural networks -- Feature selection -- Sparse regularization -- Semi-supervised learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109265
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We introduce a general framework to incorporate attribute selection into GNNs to enhance the compacity and robustness of GNNs. We develop two kinds of GNNs, i.e., AsGCN and AsGAT for attributed graph data representation and learning. We derive a simple and effective algorithm to optimize the proposed AsGCN and AsGAT. Abstract: 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 desired to extract meaningful features and eliminate noisy ones for GNN's layer-wise propagation. Based on this observation, in this paper, we combine ℓ 2, 1 / ℓ 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. Moreover, an effective optimization framework has also been derived to train the proposed AsGNNs. The proposed 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. Experimental results on several benchmark datasets demonstrate the effectiveness of the proposed AsGNNs (AsGCN, AsGAT) on semi-supervised learning tasks.