[rfp1461] hasa: hardness and structure-aware contrastive knowledge graph embedding
Published 3 months ago • 56 plays • Length 3:01Download video MP4
Download video MP3
Similar videos
-
![[rfp0950] graph contrastive learning with cohesive subgraph awareness](https://i.ytimg.com/vi/XLaXTIMSG_0/mqdefault.jpg)
2:59
[rfp0950] graph contrastive learning with cohesive subgraph awareness
-
![[rfp1465] bridging the space gap: unifying geometry knowledge graph embedding with optimal transport](https://i.ytimg.com/vi/l90KcW6RE_s/mqdefault.jpg)
2:37
[rfp1465] bridging the space gap: unifying geometry knowledge graph embedding with optimal transport
-
2:00
kdd 2023 - exploiting relation-aware attribute representation learning in knowledge graph embedding
-
14:43
dirie: knowledge graph embedding with dirichlet distribution
-
![[rfp0620] poisoning attack on federated knowledge graph embedding](https://i.ytimg.com/vi/tYzCEhX2dyc/mqdefault.jpg)
2:25
[rfp0620] poisoning attack on federated knowledge graph embedding
-
![[rfp0760] fact embedding through diffusion model for knowledge graph completion](https://i.ytimg.com/vi/4NbCBJIAW3g/mqdefault.jpg)
1:37
[rfp0760] fact embedding through diffusion model for knowledge graph completion
-
17:13
knowledge graphs - 6.3 knowledge graph completion
-
4:53
chw 04.07 image series
-
10:33
part 1: transe
-
![[rfp1797] high-frequency-aware hierarchical contrastive selective coding for representation learning](https://i.ytimg.com/vi/30xh8aij9kQ/mqdefault.jpg)
2:41
[rfp1797] high-frequency-aware hierarchical contrastive selective coding for representation learning
-
![[rfp1620] a simple but effective approach for unsupervised few-shot graph classification](https://i.ytimg.com/vi/rxcgO2DCtnA/mqdefault.jpg)
2:27
[rfp1620] a simple but effective approach for unsupervised few-shot graph classification
-
![[rfp1562] unleashing the power of knowledge graph for recommendation via invariant learning](https://i.ytimg.com/vi/MvTcJgOGEC4/mqdefault.jpg)
2:18
[rfp1562] unleashing the power of knowledge graph for recommendation via invariant learning