https://arxiv.org/abs/2305.14321
ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings
We propose ConGraT(Contrastive Graph-Text pretraining), a general, self-supervised method for jointly learning separate representations of texts and nodes in a parent (or ``supervening'') graph, where each text is associated with one of the nodes. Datasets
arxiv.org
'Paper > Multimodal Learning' 카테고리의 다른 글
| [MMML] Multimodal Deep Learning (ICML2011) (0) | 2022.05.17 |
|---|---|
| [ML] RBM & sparse RBM (0) | 2022.05.16 |
| [MMML] Multimodal Machine Learning Introduction (CMU LTI-11777 Lecture1.1) (0) | 2022.05.10 |
