A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning. (arXiv:2106.06312v2 [cs.LG] UPDATED)

Federated learning is a learning paradigm to enable collaborative learning
across different parties without revealing raw data. Notably, \textit{vertical
federated learning} (VFL), where parties share the same set of samples but only
hold partial features, has a wide range of real-world applications. However,
most existing studies in VFL disregard the "record linkage" process. They
design algorithms either assuming the data from different parties can be
exactly linked or simply linking each record with its most similar neighboring
record. These approaches …

design federated learning similarity