node2vec: Scalable Feature Learning for Networks. Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning approaches are not expressive enough to capture the diversity of connectivity patterns observed in networks. Here we propose node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks. In node2vec, we learn a mapping of nodes to a low-dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes. We define a flexible notion of a node’s network neighborhood and design a biased random walk procedure, which efficiently explores diverse neighborhoods. Our algorithm generalizes prior work which is based on rigid notions of network neighborhoods, and we argue that the added flexibility in exploring neighborhoods is the key to learning richer representations. We demonstrate the efficacy of node2vec over existing state-of-the-art techniques on multi-label classification and link prediction in several real-world networks from diverse domains. Taken together, our work represents a new way for efficiently learning state-of-the-art task-independent representations in complex networks.

References in zbMATH (referenced in 79 articles )

Showing results 21 to 40 of 79.
Sorted by year (citations)
  1. Sun, Xin; Yu, Yongbo; Liang, Yao; Dong, Junyu; Plant, Claudia; Böhm, Christian: Fusing attributed and topological global-relations for network embedding (2021)
  2. Wang, Lili; Huang, Chenghan; Ma, Weicheng; Liu, Ruibo; Vosoughi, Soroush: Hyperbolic node embedding for temporal networks (2021)
  3. Wang, Qingxiang; Kaliszyk, Cezary: JEFL: joint embedding of formal proof libraries (2021)
  4. Wei, Maosheng; Wu, Jun; Yang, Lina; Tang, Yuanyan: Matrix factorization with dual-network collaborative embedding for social recommendation (2021)
  5. Wei, Shaowei; Yu, Guoxian; Wang, Jun; Domeniconi, Carlotta; Zhang, Xiangliang: Multiple clusterings of heterogeneous information networks (2021)
  6. Xiao, Yunpeng; Li, Rui; Lu, Xingyu; Liu, Yanbing: Link prediction based on feature representation and fusion (2021)
  7. Xu, Mengjia: Understanding graph embedding methods and their applications (2021)
  8. Yukuo Cen, Zhenyu Hou, Yan Wang, Qibin Chen, Yizhen Luo, Xingcheng Yao, Aohan Zeng, Shiguang Guo, Peng Zhang, Guohao Dai, Yu Wang, Chang Zhou, Hongxia Yang, Jie Tang: CogDL: An Extensive Toolkit for Deep Learning on Graphs (2021) arXiv
  9. Zhao, Xingwang; Liang, Jiye; Wang, Jie: A community detection algorithm based on graph compression for large-scale social networks (2021)
  10. Zhou, Yinzuo; Wu, Chencheng; Tan, Lulu: Biased random walk with restart for link prediction with graph embedding method (2021)
  11. Adriaens, Florian; De Bie, Tijl; Gionis, Aristides; Lijffijt, Jefrey; Matakos, Antonis; Rozenshtein, Polina: Relaxing the strong triadic closure problem for edge strength inference (2020)
  12. Aggarwal, Charu C.: Linear algebra and optimization for machine learning. A textbook (2020)
  13. Ananyeva, Marina; Makarov, Ilya; Pendiukhov, Mikhail: GSM: inductive learning on dynamic graph embeddings (2020)
  14. Bacciu, Davide; Errica, Federico; Micheli, Alessio; Podda, Marco: A gentle introduction to deep learning for graphs (2020)
  15. Bedru, Hayat Dino; Yu, Shuo; Xiao, Xinru; Zhang, Da; Wan, Liangtian; Guo, He; Xia, Feng: Big networks: a survey (2020)
  16. Benedek Rozemberczki, Oliver Kiss, Rik Sarkar: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (2020) arXiv
  17. Chen, Yiqi; Qian, Tieyun: Relation constrained attributed network embedding (2020)
  18. Chunaev, Petr: Community detection in node-attributed social networks: a survey (2020)
  19. Comin, Cesar H.; Peron, Thomas; Silva, Filipi N.; Amancio, Diego R.; Rodrigues, Francisco A.; Costa, Luciano da F.: Complex systems: features, similarity and connectivity (2020)
  20. Gao, Chongming; Zhang, Zhong; Huang, Chen; Yin, Hongzhi; Yang, Qinli; Shao, Junming: Semantic trajectory representation and retrieval via hierarchical embedding (2020)