FeCoSR replaces one-to-one transfer with federated pretraining using Semantic Soft Cross-Entropy and local fine-tuning to avoid source degradation and negative transfer in cross-market sequential recommendation.
Title resolution pending
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
-
From Transfer to Collaboration: A Federated Framework for Cross-Market Sequential Recommendation
FeCoSR replaces one-to-one transfer with federated pretraining using Semantic Soft Cross-Entropy and local fine-tuning to avoid source degradation and negative transfer in cross-market sequential recommendation.