FedUTR fuses textual item representations with user interactions via fusion and adaptation modules to improve federated recommendations under high sparsity, with up to 59% gains over baselines and convergence guarantees.
A multi-modal prompt-tuning framework for non-overlapping multi-domain recommendation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FedUTR: Federated Recommendation with Augmented Universal Textual Representation for Sparse Interaction Scenarios
FedUTR fuses textual item representations with user interactions via fusion and adaptation modules to improve federated recommendations under high sparsity, with up to 59% gains over baselines and convergence guarantees.