DeepWalk
Bryan Perozzi, Rami Al-Rfou, Steven Skiena · ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · 2014
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.
Cited by 8,675 works. doi:10.1145/2623330.2623732 Open-access PDF
References
- ImageNet classification with deep convolutional neural networks
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
- Efficient Estimation of Word Representations in Vector Space
- Distributed Representations of Words and Phrases and their Compositionality
- A unified architecture for natural language processing
- Representation Learning: A Review and New Perspectives
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
- Anomaly detection
- Modularity and community structure in networks
- A Scalable Hierarchical Distributed Language Model