Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec

@inproceedings{Qiu2018NetworkEA,
  title={Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec},
  author={Jiezhong Qiu and Yuxiao Dong and Hao Ma and Jian Li and Kuansan Wang and Jie Tang},
  booktitle={WSDM},
  year={2018}
}
Since the invention of word2vec, the skip-gram model has significantly advanced the research of network embedding, such as the recent emergence of the DeepWalk, LINE, PTE, and node2vec approaches. In this work, we show that all of the aforementioned models with negative sampling can be unified into the matrix factorization framework with closed forms. Our analysis and proofs reveal that: (1) DeepWalk empirically produces a low-rank transformation of a network's normalized Laplacian matrix; (2… CONTINUE READING
Highly Cited
This paper has 69 citations. REVIEW CITATIONS

Citations

Publications citing this paper.

70 Citations

05020172018
Citations per Year
Semantic Scholar estimates that this publication has 70 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-9 of 9 references

The BioGRID interaction database: 2011 update

  • Chris Stark, Bobby-Joe Breitkreutz, +7 authors Xiaoqi Shi
  • Nucleic acids research 39,
  • 2010
Highly Influential
5 Excerpts

Mining multi-label data. In Data mining and knowledge discovery handbook

  • Grigorios Tsoumakas, Ioannis Katakis, Ioannis Vlahavas
  • 2009
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…