DeepWalk: online learning of social representations

@article{Perozzi2014DeepWalkOL,
  title={DeepWalk: online learning of social representations},
  author={Bryan Perozzi and Rami Al-Rfou' and Steven Skiena},
  journal={ArXiv},
  year={2014},
  volume={abs/1403.6652}
}
We present DeepWalk, a novel approach for learning latent representations of vertices in a network. These latent representations encode social relations in a continuous vector space, which is easily exploited by statistical models. DeepWalk generalizes recent advancements in language modeling and unsupervised feature learning (or deep learning) from sequences of words to graphs. DeepWalk uses local information obtained from truncated random walks to learn latent representations by treating… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • DeepWalk's representations can provide F1 scores up to 10% higher than competing methods when labeled data is sparse.
  • DeepWalk s representations can provide F1 scores up to 10% higher than competing methods when la­beled data is sparse.

Citations

Publications citing this paper.
SHOWING 1-10 OF 1,325 CITATIONS

Attributed Network Embedding via Subspace Discovery

VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Exploiting Textual Content in Academic Citation Networks

VIEW 16 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Knowledge Representation of G-Protein-Coupled Receptor Signal Transduction Pathways

  • 2019 IEEE 13th International Conference on Semantic Computing (ICSC)
  • 2019
VIEW 9 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Learning Graph Embedding with Adversarial Training Methods

  • ArXiv
  • 2019
VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Multi-Path Relationship Preserved Social Network Embedding

  • IEEE Access
  • 2019
VIEW 16 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Unsupervised Adversarial Graph Alignment with Graph Embedding

  • ArXiv
  • 2019
VIEW 13 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 536 Highly Influenced Citations

  • Averaged 394 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-4 OF 4 REFERENCES