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
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
FedMM applies a residual quantized VAE with a global federated codebook and local market-specific codebooks to transmit discrete codes that capture shared and specific collaborative patterns for improved CTR prediction across markets.
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.
-
FedMM: Federated Collaborative Signal Quantization for Multi-Market CTR Prediction
FedMM applies a residual quantized VAE with a global federated codebook and local market-specific codebooks to transmit discrete codes that capture shared and specific collaborative patterns for improved CTR prediction across markets.