GraphSage

A GraphSage is a Spatial Graph Convolutional Network that uses a sampling algorithm to obtain a fixed number of neighbors for each node.

• Context:
  • It was first introduced by Hamilton et al. (2017).
• Example(s):
  • …
• Counter-Example(s):
  • a PATCHY-SAN,
  • a Message Passing Neural Network,
  • a Diffusion Convolutional Neural Network,
  • a Learnable Graph Convolutional Network,
  • a Spectral Graph Convolutional Network,
  • a Graph Attention Network (GAT),
  • a Graph Recurrent Network (GRN),
  • a Graph Wavelet Neural Network (GWNN).
• See: Recurrent Neural Network, Feedforward Neural Network, Attention Mechanism.

---

---

References

2020a

• (Wu et al., 2020) ⇒ Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S. Yu (2020). "A Comprehensive Survey on Graph Neural Networks". In: IEEE transactions on neural networks and learning systems, 32(1), 4-24.
  • QUOTE: As the number of neighbors of a node can vary from one to a thousand or even more, it is inefficient to take the full size of a node's neighborhood. GraphSage (Hamilton et al., 2017) adopts sampling to obtain a fixed number of neighbors for each node.

2020b

• (Zhou et al., 2020) ⇒ Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun (2020). "Graph neural networks: A review of methods and applications". AI Open, 1, 57-81.
  • QUOTE: GraphSAGE (Hamilton et al., 2017a) is a general inductive framework which generates embeddings by sampling and aggregating features from a node's local neighborhood.

2019

• (Zhang et al., 2019) ⇒ Si Zhang, Hanghang Tong, Jiejun Xu, and Ross Maciejewski (2019). "Graph convolutional networks: a comprehensive review". In: Computational Social Networks, 6(1), 1-23.

2017

• (Hamilton et al., 2017) ⇒ William L. Hamilton, Rex Ying, and Jure Leskovec (2017). "Inductive Representation Learning on Large Graphs". In: Proceeding of the 31st Conference on Neural Information Processing Systems (NIPS 2017).

---