Graph Neural Network (Network Analysis)
A Graph Neural Network (GNN) is a deep learning architecture that operates directly on graph-structured data by combining node features with structural information through iterative neighborhood message passing. The three canonical variants — the Graph Convolutional Network (GCN) introduced by Kipf and Welling in 2017, the Graph Attention Network (GAT) introduced by Veličković et al. in 2018, and GraphSAGE — differ in how they aggregate neighbor information: GCN applies a spectral convolution over the full adjacency, GAT weights neighbors by learned attention scores, and GraphSAGE samples and aggregates local neighborhoods inductively, enabling generalization to unseen nodes.
원본 기록
방법의 원본 기록에서 그대로 복사된 인용입니다. 이로부터 수준별 검증이 추론되지 않습니다.
- Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR). · DOI 10.48550/arXiv.1609.02907
- Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2018). Graph Attention Networks. International Conference on Learning Representations (ICLR). · DOI 10.48550/arXiv.1710.10903
- Hamilton, W.L. (2020). Graph Representation Learning. Morgan & Claypool. · DOI 10.1007/978-3-031-01588-5
큐레이션된 주장
각각 자체 평가와 함께 증거 원장에 유지된 주장입니다.
원장에 주장 평가가 없는 경우 이 보기에서는 주장 평가를 만들지 않습니다.
관련 방법
방법 그래프에서 생성되었으며 기계가 제안한 관계로 표시됩니다 — 증거 주장이 추론되지 않습니다.