Rank-based self-training for graph convolutional networks

Author(s)

Guimaraes Pedronette, Daniel Carlos ^[1] ; Latecki, Longin Jan ^[2]

Affiliation

^[1] Sao Paulo State Univ, UNESP, Dept Stat Appl Math & Comp DEMAC, Rio Claro - Brazil

^[2] Temple Univ, Dept Comp & Informat Sci, Philadelphia, PA 19122 - USA

• Document type: Journal article
• Source: INFORMATION PROCESSING & MANAGEMENT; v. 58, n. 2 MAR 2021.
• Web of Science Citations: 0

Abstract

Graph Convolutional Networks (GCNs) have been established as a fundamental approach for representation learning on graphs, based on convolution operations on non-Euclidean domain, defined by graph-structured data. GCNs and variants have achieved state-of-the-art results on classification tasks, especially in semi-supervised learning scenarios. A central challenge in semi supervised classification consists in how to exploit the maximum of useful information encoded in the unlabeled data. In this paper, we address this issue through a novel self-training approach for improving the accuracy of GCNs on semi-supervised classification tasks. A margin score is used through a rank-based model to identify the most confident sample predictions. Such predictions are exploited as an expanded labeled set in a second-stage training step. Our model is suitable for different GCN models. Moreover, we also propose a rank aggregation of labeled sets obtained by different GCN models. The experimental evaluation considers four GCN variations and traditional benchmarks extensively used in the literature. Significant accuracy gains were achieved for all evaluated models, reaching results comparable or superior to the state-of-theart. The best results were achieved for rank aggregation self-training on combinations of the four GCN models. (AU)

• FAPESP's process: 17/25908-6 - Weakly supervised learning for compressed video analysis on retrieval and classification tasks for visual alert
• Grantee: João Paulo Papa
• Support Opportunities: Research Grants - Research Partnership for Technological Innovation - PITE
• FAPESP's process: 18/15597-6 - Aplication and investigation of unsupervised learning methods in retrieval and classification tasks
• Grantee: Daniel Carlos Guimarães Pedronette
• Support Opportunities: Research Grants - Young Investigators Grants - Phase 2