Corpus ID: 1343259

From random walks to distances on unweighted graphs

@inproceedings{Hashimoto2015FromRW,
  title={From random walks to distances on unweighted graphs},
  author={T. Hashimoto and Y. Sun and T. Jaakkola},
  booktitle={NIPS},
  year={2015}
}
  • T. Hashimoto, Y. Sun, T. Jaakkola
  • Published in NIPS 2015
  • Mathematics, Computer Science
  • Large unweighted directed graphs are commonly used to capture relations between entities. A fundamental problem in the analysis of such networks is to properly define the similarity or dissimilarity between any two vertices. Despite the significance of this problem, statistical characterization of the proposed metrics has been limited. We introduce and develop a class of techniques for analyzing random walks on graphs using stochastic calculus. Using these techniques we generalize results on… CONTINUE READING

    Figures and Topics from this paper.

    Word Embeddings as Metric Recovery in Semantic Spaces
    • 42
    • PDF
    A bag-of-paths framework for network data analysis
    • 25
    • PDF
    Exploration of a Graph-based Density-sensitive Metric
    • 1
    • PDF
    Intrinsic Metrics: Exact Equality between a Geodesic Metric and a Graph metric
    • 1
    net4Lap: Neural Laplacian Regularization for Ranking and Re-Ranking
    • 2
    • PDF
    Link Prediction via Factorization Machines
    • 1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES
    Link Prediction in Complex Networks: A Survey
    • 1,711
    • PDF
    Markov Processes: Characterization and Convergence
    • 4,465
    • PDF
    Handbook of Brownian Motion - Facts and Formulae
    • 1,624
    • PDF
    Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables
    • 17,306
    • PDF
    Consistency of spectral clustering
    • 450
    • PDF
    Hitting and commute times in large random neighborhood graphs
    • 74
    • Highly Influential
    • PDF
    A family of dissimilarity measures between nodes generalizing both the shortest-path and the commute-time distances
    • 87
    • PDF
    A Tractable Approach to Finding Closest Truncated-commute-time Neighbors in Large Graphs
    • 85
    • PDF
    Learning from labeled and unlabeled data on a directed graph
    • 395
    • PDF