2023
DOI: 10.1016/j.asoc.2023.110832
|View full text |Cite
|
Sign up to set email alerts
|

Deep Autoencoder-like non-negative matrix factorization with graph regularized for link prediction in dynamic networks

Laishui Lv,
Dalal Bardou,
Yanqiu Liu
et al.
Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 59 publications
0
2
0
Order By: Relevance
“…This method effectively combines the encoder and decoder components under a single loss function framework. Ye and his colleagues [25] took an additional step and innovatively developed a new category of deep autoencoder NMF (DANMF) models for community detection tasks. This model extends Sun's NNSED approach by constructing a framework like that of a deep autoencoder.…”
Section: Learning-model-based Community Detectionmentioning
confidence: 99%
“…This method effectively combines the encoder and decoder components under a single loss function framework. Ye and his colleagues [25] took an additional step and innovatively developed a new category of deep autoencoder NMF (DANMF) models for community detection tasks. This model extends Sun's NNSED approach by constructing a framework like that of a deep autoencoder.…”
Section: Learning-model-based Community Detectionmentioning
confidence: 99%
“…In addition, it can also bridge the gap between low-level to highlevel networks for optimal community detection [20]. The deep autoencoder consists of two components: an encoder component and a decoder component [21]. By employing layer-by-layer encoding, a high-dimensional dataset is transformed into a low-dimensional encoding, which can then be reconstructed back to its original high-dimensional form using layer-by-layer decoding.…”
Section: Introductionmentioning
confidence: 99%