Corpus ID: 174798401

Wasserstein Weisfeiler-Lehman Graph Kernels

@inproceedings{Togninalli2019WassersteinWG,
  title={Wasserstein Weisfeiler-Lehman Graph Kernels},
  author={Matteo Togninalli and M. Elisabetta Ghisu and Felipe Llinares-L{\'o}pez and Bastian Rieck and Karsten M. Borgwardt},
  booktitle={NeurIPS},
  year={2019}
}
  • Matteo Togninalli, M. Elisabetta Ghisu, +2 authors Karsten M. Borgwardt
  • Published in NeurIPS 2019
  • Mathematics, Computer Science, Biology
  • Most graph kernels are an instance of the class of $\mathcal{R}$-Convolution kernels, which measure the similarity of objects by comparing their substructures. Despite their empirical success, most graph kernels use a naive aggregation of the final set of substructures, usually a sum or average, thereby potentially discarding valuable information about the distribution of individual components. Furthermore, only a limited instance of these approaches can be extended to continuously attributed… CONTINUE READING

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

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-3 OF 3 CITATIONS

    Convolutional Kernel Networks for Graph-Structured Data

    VIEW 5 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    A Wasserstein Subsequence Kernel for Time Series

    VIEW 1 EXCERPT
    CITES METHODS

    Neural Subgraph Isomorphism Counting

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES

    Faster Kernels for Graphs with Continuous Attributes via Hashing

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    E

    • N. Shervashidze, P. Schweitzer
    • J. v. Leeuwen, K. Mehlhorn, and K. M. Borgwardt. Weisfeilerlehman graph kernels. Journal of Machine Learning Research, 12(Sep):2539–2561
    • 2011
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Fast subtree kernels on graphs

    VIEW 4 EXCERPTS