방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 그래프 신경망을 이용한 전이 학습× | 그래프 신경망× | |
|---|---|---|
| 분야≠ | 딥러닝 | 네트워크 분석 |
| 계열≠ | Machine learning | Process / pipeline |
| 기원 연도≠ | 2010–2020 | 2017–2018 (major variants) |
| 창시자≠ | Hu et al. (GNN-specific); Pan & Yang (transfer learning framework) | — |
| 유형≠ | Transfer learning / graph representation learning | Deep learning on graph-structured data |
| 원전≠ | Hu, W., Liu, B., Gomes, J., Zitnik, M., Liang, P., Pande, V., & Leskovec, J. (2020). Strategies for Pre-training Graph Neural Networks. In International Conference on Learning Representations (ICLR 2020). link ↗ | Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR). DOI ↗ |
| 별칭≠ | TL-GNN, pre-trained GNN, GNN transfer learning, graph transfer learning | GNN, GCN, GAT, GraphSAGE |
| 관련≠ | 3 | 5 |
| 요약≠ | Transfer Learning with Graph Neural Networks (GNNs) adapts a GNN pre-trained on a large source graph dataset to a smaller, often label-scarce target graph task. By reusing learned node and edge representations, this approach achieves strong predictive performance where collecting sufficient labeled graph data is expensive or slow — as is common in chemistry, biology, and social 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. |
| ScholarGate데이터셋 ↗ |
|
|