· 2014
DeepWalk
- 8,560citations
- 2014year
Short summary
DeepWalk learns continuous vector representations of network nodes that capture their social relations, generalizing word embedding techniques to graph data.
AI-generated from the title and abstract; the full text is not read.
Key points
- DeepWalk generates latent representations for network vertices.
- These representations are continuous vectors capturing social relations.
- The method generalizes word embedding techniques from language modeling to graphs.
- The learned vectors are easily exploitable by statistical models.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source., 2014 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science