DeepWalk

DeepWalk: Online Learning of Social Representations. 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 F1 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.


References in zbMATH (referenced in 42 articles )

Showing results 1 to 20 of 42.
Sorted by year (citations)

1 2 3 next

  1. Guo, Xiaoyang; Srivastava, Anuj; Sarkar, Sudeep: A quotient space formulation for generative statistical analysis of graphical data (2021)
  2. Han, Xinyu; Zhao, Yi; Small, Michael: Revisiting the memory capacity in reservoir computing of directed acyclic network (2021)
  3. Li, Jianxin; Ji, Cheng; Peng, Hao; He, Yu; Song, Yangqiu; Zhang, Xinmiao; Peng, Fanzhang: RWNE: a scalable random-walk based network embedding framework with personalized higher-order proximity preserved (2021)
  4. Mercurio, Paula; Liu, Di: Identifying transition states of chemical kinetic systems using network embedding techniques (2021)
  5. Wang, Yuyao; Bu, Zhan; Yang, Huan; Li, Hui-Jia; Cao, Jie: An effective and scalable overlapping community detection approach: integrating social identity model and game theory (2021)
  6. Zhu, Yuanyuan; Hu, Bin; Chen, Lei; Dai, Qi: iMPTCE-Hnetwork: a multilabel classifier for identifying metabolic pathway types of chemicals and enzymes with a heterogeneous network (2021)
  7. Ananyeva, Marina; Makarov, Ilya; Pendiukhov, Mikhail: GSM: inductive learning on dynamic graph embeddings (2020)
  8. Bedru, Hayat Dino; Yu, Shuo; Xiao, Xinru; Zhang, Da; Wan, Liangtian; Guo, He; Xia, Feng: Big networks: a survey (2020)
  9. Chen, Yiqi; Qian, Tieyun: Relation constrained attributed network embedding (2020)
  10. Fu, Sichao; Liu, Weifeng; Tao, Dapeng; Zhou, Yicong; Nie, Liqiang: HesGCN: Hessian graph convolutional networks for semi-supervised classification (2020)
  11. Han, Xiao; Zhang, Chunhong; Guo, Chenchen; Ji, Yang; Hu, Zheng: Distributed representation of knowledge graphs with subgraph-aware proximity (2020)
  12. Interdonato, Roberto; Magnani, Matteo; Perna, Diego; Tagarelli, Andrea; Vega, Davide: Multilayer network simplification: approaches, models and methods (2020)
  13. Juda, Mateusz: Unsupervised features learning for sampled vector fields (2020)
  14. Kazemi, Seyed Mehran; Goel, Rishab; Jain, Kshitij; Kobyzev, Ivan; Sethi, Akshay; Forsyth, Peter; Poupart, Pascal: Representation learning for dynamic graphs: a survey (2020)
  15. Lavrač, Nada; Škrlj, Blaž; Robnik-Šikonja, Marko: Propositionalization and embeddings: two sides of the same coin (2020)
  16. Lee, O-Joun; Jung, Jason J.: Story embedding: learning distributed representations of stories based on character networks (2020)
  17. Li, Bentian; Pi, Dechang; Lin, Yunxia; Khan, Izhar Ahmed; Cui, Lin: Multi-source information fusion based heterogeneous network embedding (2020)
  18. Li, Ming; Ma, Zheng; Wang, Yu Guang; Zhuang, Xiaosheng: Fast Haar transforms for graph neural networks (2020)
  19. Lv, Shaoqing; Xiang, Ju; Feng, Jingyu; Wang, Honggang; Lu, Guangyue; Li, Min: Community enhancement network embedding based on edge reweighting preprocessing (2020)
  20. Lyu, Hanbaek; Needell, Deanna; Balzano, Laura: Online matrix factorization for Markovian data and applications to network dictionary learning (2020)

1 2 3 next