Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management 2021
DOI: 10.1145/3459637.3482424
|View full text |Cite
|
Sign up to set email alerts
|

DisenKGAT

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 49 publications
(13 citation statements)
references
References 28 publications
0
13
0
Order By: Relevance
“…For example, gene embeddings obtained through the KG graph is coupled and this has an impact on both interpretability and performance. To further improve this drawback in future work, we will attempt to use the decoupling representation learning, similar to that described in DisenKGAT ( Wu et al , 2021 ), to achieve higher quality gene embeddings. In addition, due to the sparsity of the SL graph, negative samples were created using theoretical considerations and may contain potential positive samples.…”
Section: Conclusion and Discussionmentioning
confidence: 99%
“…For example, gene embeddings obtained through the KG graph is coupled and this has an impact on both interpretability and performance. To further improve this drawback in future work, we will attempt to use the decoupling representation learning, similar to that described in DisenKGAT ( Wu et al , 2021 ), to achieve higher quality gene embeddings. In addition, due to the sparsity of the SL graph, negative samples were created using theoretical considerations and may contain potential positive samples.…”
Section: Conclusion and Discussionmentioning
confidence: 99%
“…Inspired by recent progress in disentangled representation learning [32,46,48], we seek graph disentanglement for context-aware event forecasting. Most existing works solely rely on the inherent structural information for graph disentanglement.…”
Section: Context-aware Graphmentioning
confidence: 99%
“…Most existing works solely rely on the inherent structural information for graph disentanglement. For example, MaridVAE [33] and DGCF [45] utilize the user-item interactions to learn disentangled representations for different intents; DisenKGAT [48] tackles the heterogeneous knowledge graph and disentangles the entity embedding with respect to different topics and clusters. Nonetheless, these methods are incapable of disentangling event graphs since the events are too coarse-grained, and pure structural information is unable to well disentangle the graph.…”
Section: Context-aware Graphmentioning
confidence: 99%
See 1 more Smart Citation
“…Graph Neural Network (GNN) is an emerging deep learning method for graph-structured data presentation [11]. Recently, it has been successfully applied in different fields of graphstructured data, like recommendation system [12], social network [13], knowledge map [14], etc. However, little attention has been paid to introducing GNN into IP geolocation.…”
Section: Measurement-based Ip Geolocation Can Geolocate a Targetmentioning
confidence: 99%