Asgarali Bouyer
Biographic Data
| ID | 10056057 |
|---|---|
| NAME | Asgarali Bouyer |
| GIVEN NAMES | Asgarali |
| FAMILY NAME | Bouyer |
| SIGNATURE | BOUYER A |
| AFFILIATIONS | Azarbaijan Shahid Madani University |
| ORCID | 0000-0002-4808-2856 |
| VERIFIED | Yes |
| TOTAL WORKS | 2 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 2 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2025 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 0 |
AdaDCL
Graph contrastive learning has demonstrated outstanding performance in addressing the issue of label scarcity. It still has two limitations: 1) the stacking of graph layers often leads to over-smoothing, hard to distinguish the embeddings of distinct nodes; and 2) traditional algorithms typically model user preferences with a unified intention, neglecting the multifaceted and fine-grained motivations behind user-item interactions. To overcome the…
Identifying Key Nodes Based on Neighborhood Topology and Voting Mechanism in Complex Networks
Large-scale networks cannot be effectively addressed by global structure-based techniques due to their high temporal complexity, while local structure-based methods may overlook global information. To overcome these limitations, we propose a novel key node identification method for complex networks, named cycle structure, voting mechanism, ranking principle (CVR). This method adopts a multilevel processing approach and an enhanced voting mechanis…
No prominent works on this page.
Identifying Key Nodes Based on Neighborhood Topology and Voting Mechanism in Complex Networks
Large-scale networks cannot be effectively addressed by global structure-based techniques due to their high temporal complexity, while local structure-based methods may overlook global information. To overcome these limitations, we propose a novel key node identification method for complex networks, named cycle structure, voting mechanism, ranking principle (CVR). This method adopts a multilevel processing approach and an enhanced voting mechanis…
AdaDCL
Graph contrastive learning has demonstrated outstanding performance in addressing the issue of label scarcity. It still has two limitations: 1) the stacking of graph layers often leads to over-smoothing, hard to distinguish the embeddings of distinct nodes; and 2) traditional algorithms typically model user preferences with a unified intention, neglecting the multifaceted and fine-grained motivations behind user-item interactions. To overcome the…
Computer Science (2 works) · Artificial Intelligence (1 work) · Complex network (1 work) · Computer network (1 work) · Computer security (1 work) · Distributed computing (1 work) · Engineering (1 work) · Machine Learning in Healthcare (1 work) · Natural language processing (1 work) · Network topology (1 work)