Federated learning-based regularized adversarial graph embedding for cross-social network user alignment

doi:10.1016/j.chaos.2025.117515

Federated learning-based regularized adversarial graph embedding for cross-social network user alignment

2025-10-31

0

PRE

AI

DOI：10.1016/j.chaos.2025.117515

Original

Original request for help

Save

Abstract

En 中文

• Propose the FAUA method for cross-social network user alignment. • The FAUA addresses privacy protection and data silo challenges. • Design an adversarial regularization module to enhance performance. • Eliminate reliance on unreliable user attributes by using only network structure. • Validate the superiority of the FAUA over baseline method by experiments.

Federated learning-based regularized adversarial graph embedding for cross-social network user alignment

Abstract

Journal

Organization