SCIENCE@home

Representation Learning over Dynamic Graphs

Rakshit S. Trivedi,Mehrdad Farajtabar,P. Biswal,H. Zha

Published 2018 in arXiv.org

ABSTRACT

How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently produce low-dimensional node embeddings that evolves over time. The learned embeddings drive the dynamics of two key processes namely, communication and association between nodes in dynamic graphs. These processes exhibit complex nonlinear dynamics that evolve at different time scales and subsequently contribute to the update of node embeddings. We employ a time-scale dependent multivariate point process model to capture these dynamics. We devise an efficient unsupervised learning procedure and demonstrate that our approach significantly outperforms representative baselines on two real-world datasets for the problem of dynamic link prediction and event time prediction.

PUBLICATION RECORD

  • Publication year

    2018

  • Venue

    arXiv.org

  • Publication date

    2018-03-11

  • Fields of study

    Mathematics, Computer Science

  • Identifiers
    arXiv 1803.04051
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-46 of 46 references · Page 1 of 1

CITED BY

Showing 1-59 of 59 citing papers · Page 1 of 1