Sparsity-Induced Graph Convolutional Network for Semisupervised Learning

Recommended citation: Zhou, J., Zeng, S., & Zhang, B. (2021). Sparsity-Induced Graph Convolutional Network for Semisupervised Learning. IEEE Transactions on Artificial Intelligence, 2(6), 549-563.

Download paper here

The two-stage strategy has been widely used in image classification. However, these methods barely take the classification criteria of the first stage into consideration in the second prediction stage. In this paper, we propose a novel Two-Stage Representation method (TSR), and convert it to a Single-Teacher SingleStudent (STSS) problem in our two-stage knowledge transfer framework for image classification.