Corpus ID: 220424574

Learning Graph Structure With A Finite-State Automaton Layer

@article{Johnson2020LearningGS,
  title={Learning Graph Structure With A Finite-State Automaton Layer},
  author={D. Johnson and H. Larochelle and Daniel Tarlow},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.04929}
}
  • D. Johnson, H. Larochelle, Daniel Tarlow
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Graph-based neural network models are producing strong results in a number of domains, in part because graphs provide flexibility to encode domain knowledge in the form of relational structure (edges) between nodes in the graph. In practice, edges are used both to represent intrinsic structure (e.g., abstract syntax trees of programs) and more abstract relations that aid reasoning for a downstream task (e.g., results of relevant program analyses). In this work, we study the problem of learning… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES
    Use of a simple method for sampling cuticular hydrocarbons from live social wasps
    34
    Gated Graph Sequence Neural Networks
    1016
    Global Relational Models of Source Code
    10
    JAX: composable transformations of Python+NumPy programs
    • 2018
    Learning to Represent Programs with Graphs
    198
    Neural Relational Inference for Interacting Systems
    174