DeepWalk: Online Learning of Social Representations

26 Mar 2014Bryan PerozziRami Al-RfouSteven Skiena

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... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Node Classification BlogCatalog DeepWalk Accuracy 22.50% # 3
Node Classification BlogCatalog DeepWalk Macro-F1 0.214 # 4
Node Classification Citeseer DeepWalk Accuracy 43.2% # 23
Node Classification Cora DeepWalk Accuracy 67.2% # 25
Document Classification Cora DeepWalk Accuracy 67.2% # 7
Node Classification NELL DeepWalk Accuracy 58.1% # 3
Node Classification Pubmed DeepWalk Accuracy 65.3% # 19
Node Classification Wikipedia DeepWalk Accuracy 19.40% # 3
Node Classification Wikipedia DeepWalk Macro-F1 0.183 # 3