DeepWalk: Online Learning of Social Representations

26 Mar 2014  ·  Bryan Perozzi, Rami Al-Rfou, Steven 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. 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.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Node Classification BlogCatalog DeepWalk Accuracy 22.5% # 5
Macro-F1 0.214 # 4
Link Property Prediction ogbl-collab DeepWalk Test Hits@50 0.5037 ± 0.0034 # 13
Validation Hits@50 Please tell us # 18
Number of params 61390187 # 1
Ext. data No # 1
Link Property Prediction ogbl-ddi DeepWalk Test Hits@20 0.2246 ± 0.0290 # 15
Validation Hits@20 Please tell us # 18
Number of params 1543913 # 7
Ext. data No # 1
Link Property Prediction ogbl-ppa DeepWalk Test Hits@100 0.2302 ± 0.0163 # 8
Validation Hits@100 Please tell us # 11
Number of params 150138741 # 1
Ext. data No # 1
Node Classification Wikipedia DeepWalk Accuracy 19.4% # 3
Macro-F1 0.183 # 3

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Document Classification Cora DeepWalk Accuracy 67.2% # 7

Methods