Corpus ID: 195750912

Graph Star Net for Generalized Multi-Task Learning

@article{Lu2019GraphSN,
  title={Graph Star Net for Generalized Multi-Task Learning},
  author={Haonan Lu and Seth H. Huang and Tian Ye and Xiuyan Guo},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.12330}
}
  • Haonan Lu, Seth H. Huang, +1 author Xiuyan Guo
  • Published in ArXiv 2019
  • Computer Science
  • 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. [...] Key Result Specifically, for graph classification and link prediction, GraphStar outperforms the current state-of-the-art models by 2-5% on several key benchmarks.Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES

    Modeling Relational Data with Graph Convolutional Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Simplifying Graph Convolutional Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Large-Scale Learnable Graph Convolutional Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Multi-Task Graph Autoencoders

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Non-local Neural Networks

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Inductive Representation Learning on Large Graphs

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL