DeepWalk
Top Cited Papers
- 24 August 2014
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 701-710
- https://doi.org/10.1145/2623330.2623732
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. DeepWalk uses local information obtained from truncated random walks to learn latent representations by treating walks as the equivalent of sentences. We demonstrate DeepWalk's latent representations on several multi-label network classification tasks for social networks such as BlogCatalog, Flickr, and YouTube. Our results show that DeepWalk outperforms challenging baselines which are allowed a global view of the network, especially in the presence of missing information. DeepWalk's representations can provide $F_1$ scores up to 10% higher than competing methods when labeled data is sparse. In some experiments, DeepWalk's representations are able to outperform all baseline methods while using 60% less training data. DeepWalk is also scalable. It is an online learning algorithm which builds useful incremental results, and is trivially parallelizable. These qualities make it suitable for a broad class of real world applications such as network classification, and anomaly detection.Comment: 10 pages, 5 figures, 4 table
Keywords
Other Versions
Funding Information
- Google (Faculty Research Award)
- Division of Information and Intelligent Systems (DBI-1060572 and IIS-1017181)
- Division of Biological Infrastructure (DBI-1060572 and IIS-1017181)
This publication has 22 references indexed in Scilit:
- Fast Random Walk Graph KernelPublished by Society for Industrial & Applied Mathematics (SIAM) ,2012
- It's who you knowPublished by Association for Computing Machinery (ACM) ,2011
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Leveraging social media networks for classificationData Mining and Knowledge Discovery, 2011
- Anomaly detectionACM Computing Surveys, 2009
- Using ghost edges for classification in sparsely labeled networksPublished by Association for Computing Machinery (ACM) ,2008
- A bias/variance decomposition for models using collective inferenceMachine Learning, 2008
- A unified architecture for natural language processingPublished by Association for Computing Machinery (ACM) ,2008
- Modularity and community structure in networksProceedings of the National Academy of Sciences of the United States of America, 2006
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1984