방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 다국어 그래프 신경망× | 그래프 신경망을 이용한 전이 학습× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2019 | 2010–2020 |
| 창시자≠ | Various (Kipf & Welling 2017 for GNN; multilingual extensions from NLP community ~2019) | Hu et al. (GNN-specific); Pan & Yang (transfer learning framework) |
| 유형≠ | Graph-based deep learning with multilingual node/edge features | Transfer learning / graph representation learning |
| 원전≠ | Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR 2017. link ↗ | 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 ↗ |
| 별칭 | Multilingual GNN, cross-lingual GNN, multilingual graph network, multilingual relational GNN | TL-GNN, pre-trained GNN, GNN transfer learning, graph transfer learning |
| 관련≠ | 5 | 3 |
| 요약≠ | A Multilingual Graph Neural Network (Multilingual GNN) applies graph-based message-passing over nodes and edges that carry features from two or more languages. It is used for tasks such as cross-lingual entity alignment, multilingual knowledge-graph completion, and relation extraction across parallel or comparable corpora, allowing structural and semantic information from multiple languages to be jointly learned. | 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. |
| ScholarGate데이터셋 ↗ |
|
|