Dengcheng Yan
Biographic Data
| ID | 10055300 |
|---|---|
| NAME | Dengcheng Yan |
| GIVEN NAMES | Dengcheng |
| FAMILY NAME | Yan |
| SIGNATURE | YAN D |
| AFFILIATIONS | Anhui University |
| ORCID | 0000-0003-1417-5269 |
| VERIFIED | Yes |
| TOTAL WORKS | 2 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 2 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2023 |
| LATEST PUBLICATION YEAR | 2024 |
| H-INDEX | 0 |
Label-Dependent Graph Neural Network
Graph neural network (GNN) provides a powerful expressive way to embed graph-structured data, which has been widely applied and spans many fields. This article found an interesting but unreasonable phenomenon in some classical GNNs, namely label confusion. Theoretically, the dependence between prediction label and ground-truth should gradually increase and tend to converge with training epochs. On the contrary, label confusion shows that the depe…
Semantic Tradeoff for Heterogeneous Graph Embedding
Recently, many data mining models based on heterogeneous graph (HG) have emerged. Among these, HG embedding is an important and indispensable process. However, the existing HG embedding models usually use graph neural network to learn embeddings separately on different meta-paths, ignoring the fact that different meta-paths contain not only their unique semantics but also related semantics. This may result in semantic overlap or irrelevance, whic…
No prominent works on this page.
Semantic Tradeoff for Heterogeneous Graph Embedding
Recently, many data mining models based on heterogeneous graph (HG) have emerged. Among these, HG embedding is an important and indispensable process. However, the existing HG embedding models usually use graph neural network to learn embeddings separately on different meta-paths, ignoring the fact that different meta-paths contain not only their unique semantics but also related semantics. This may result in semantic overlap or irrelevance, whic…
Label-Dependent Graph Neural Network
Graph neural network (GNN) provides a powerful expressive way to embed graph-structured data, which has been widely applied and spans many fields. This article found an interesting but unreasonable phenomenon in some classical GNNs, namely label confusion. Theoretically, the dependence between prediction label and ground-truth should gradually increase and tend to converge with training epochs. On the contrary, label confusion shows that the depe…
Advanced Graph Neural Networks (2 works) · Artificial Intelligence (2 works) · Complex Network Analysis Techniques (2 works) · Computer Science (2 works) · Data mining (2 works) · Graph (2 works) · Theoretical Computer Science (2 works) · Artificial neural network (1 work) · Confusion (1 work) · Data Mining Algorithms and Applications (1 work)