Graph Star Net for Generalized Multi-Task Learning
This work solves the problem of efficient and effective multi-task learning on graphs for researchers and practitioners in machine learning, though it appears incremental as it builds on existing graph neural network methods.
The authors tackled the problem of generalized multi-task learning for graph data by introducing GraphStar, a unified graph neural network architecture that addresses earlier challenges and achieves non-local representation without increasing depth or computational cost. The result showed that GraphStar outperforms state-of-the-art models by 2-5% on graph classification and link prediction benchmarks.
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.