LP-GCN is a federated GNN recommendation framework designed to replicate centralized training exactly, but its privacy guarantee is weakened by gradient information sent to the server.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Lossless and Privacy-Preserving Graph Convolution Network for Federated Item Recommendation
LP-GCN is a federated GNN recommendation framework designed to replicate centralized training exactly, but its privacy guarantee is weakened by gradient information sent to the server.