MCoGCN-motif high-order feature-guided embedding learning framework for social link prediction
Nan Xiang, Wenjing Yang, Xindi Rao · 2024
Read MCoGCN-motif high-order feature-guided embedding learning framework for social link prediction by Nan Xiang, Wenjing Yang, Xindi Rao (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-11603285.txt.
Description
Nan Xiang, Wenjing Yang, and Xindi Rao present a 2024 paper on predicting links in social networks. Most models look only at direct connections between users, missing richer patterns that involve several users at once. The team builds a framework that learns from motifs, small recurring subgraphs that capture these higher-order patterns. A simplified attention step lets the motif-based view guide the plain connection-based view of each user.
The design helps users with few direct ties, whose profiles are otherwise too thin to judge. Tests on four social networks showed strong accuracy in predicting which links will form. The authors argue that high-order structure carries real signal for link prediction. Their framework offers a way to fold that signal into standard graph learning models.
Catalog record
| CREATOR | Nan Xiang, Wenjing Yang, Xindi Rao |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |