Graph Star Net for Generalized Multi-Task Learning

Abstract

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

References in corpus (2)

• Semi-Supervised Classification with Graph Convolutional Networks
• Simplifying Graph Convolutional Networks

Cited by in corpus (7)

• Explainable Natural Language Processing with Matrix Product States
• The general theory of permutation equivarant neural networks and higher order graph variational encoders
• Quadratic GCN for Graph Classification
• NENET: An Edge Learnable Network for Link Prediction in Scene Text
• Deep Multi-Task Augmented Feature Learning via Hierarchical Graph Neural Network
• Improving Expressivity of Graph Neural Networks
• Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs