Fusing multiplex heterogeneous networks using graph attention-aware fusion networks
Ziynet Nesibe Kesimoglu, Serdar Bozdag · 2024
Read Fusing multiplex heterogeneous networks using graph attention-aware fusion networks by Ziynet Nesibe Kesimoglu, Serdar Bozdag (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11586420.txt.
Description
Ziynet Kesimoglu and Serdar Bozdag fused layered networks in 2024 so that standard graph learning tools can read them. Real networks, from biology to social media, carry several kinds of nodes and links at once, and most learning methods expect just one of each.
Their framework learns two levels of importance: which neighbors matter to each node, and which network layer matters overall. Edges are then rescored by those importances and the weakest are cut, leaving one clean fused network. A graph convolutional model runs on the result for tasks like node labeling. Across four data sets from different fields, the fused approach matched or beat leading rivals, and the learned weights can be read back for meaning.
Catalog record
| CREATOR | Ziynet Nesibe Kesimoglu, Serdar Bozdag |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |