Graph Star Net for Generalized Multi-Task Learning

• DOI: 10.48550/arxiv.1906.12330
• Publication Date: 2019-01-01
• Authors: Lu Haonan; Seth H. Huang; Ye Tian; Xiuyan Guo
• Keywords: Star (game theory); Net (polyhedron)

In this work, we present graph star net (GraphStar), a novel and unified neural architecture which utilizes message-passing relay attention mechanism for multiple prediction tasks - node classification, classification link prediction. GraphStar addresses many earlier challenges facing nets achieves non-local representation without increasing the model depth or bearing heavy computational costs. We also propose new method to tackle topic-specific sentiment analysis based on text as classification. Our work shows that 'star nodes' can learn effective graph-data improve current methods three tasks. Specifically, prediction, outperforms state-of-the-art models by 2-5% several key benchmarks.