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

Explore this paper's citation graph

Summary

The NetMF method offers significant improvements over DeepWalk and LINE for conventional network mining tasks and provides the theoretical connections between skip-gram based network embedding algorithms and the theory of graph Laplacian.

Type
preprint
Published
2017-10-09
Cited by
994
References
58
Access
Open access

Keywords

Theoretical computer science, Matrix decomposition, Computer science, Embedding, Factorization

References

Cited by

Related papers