Attention-Based Graph Convolutional Network for Zero-Shot Learning with Pre-Training. (7th December 2021)

• Record Type: Journal Article
• Authors: Wu, Xuefei; Liu, Mingjiang; Xin, Bo; Zhu, Zhangqing; Wang, Gang
• Other Names: Lolli Francesco Academic Editor.
• Is Part Of: Mathematical problems in engineering. Volume 2021(2021)
• Publication Date: 2021-12-07
• Subjects: Engineering mathematics -- Periodicals; 510.2462
• DOI: 10.1155/2021/7480712
• Languages: English
• ISSNs: 1024-123X

Abstract

Abstract : Zero-shot learning (ZSL) is a powerful and promising learning paradigm for classifying instances that have not been seen in training. Although graph convolutional networks (GCNs) have recently shown great potential for the ZSL tasks, these models cannot adjust the constant connection weights between the nodes in knowledge graph and the neighbor nodes contribute equally to classify the central node. In this study, we apply an attention mechanism to adjust the connection weights adaptively to learn more important information for classifying unseen target nodes. First, we propose an attention graph convolutional network for zero-shot learning (AGCNZ) by integrating the attention mechanism and GCN directly. Then, in order to prevent the dilution of knowledge from distant nodes, we apply the dense graph propagation (DGP) model for the ZSL tasks and propose an attention dense graph propagation model for zero-shot learning (ADGPZ). Finally, we propose a modified loss function with a relaxation factor to further improve the performance of the learned classifier. Experimental results under different pre-training settings verified the effectiveness of the proposed attention-based models for ZSL.