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
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.IR 4verdicts
UNVERDICTED 4representative citing papers
SemaCDR builds a unified semantic space with LLM-generated domain-agnostic features and adaptive fusion to improve cross-domain sequential recommendations over baselines.
LGCD creates pseudo-overlapping user data via LLM reasoning and uses conditional diffusion to generate target-domain user representations for inter-domain sequential recommendation without real overlapping users.
LLM-EDT improves cross-domain sequential recommendation by using LLMs for transferable item augmentation, dual-phase training to handle domain transitions, and domain-aware profiling to build user profiles.
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.
-
SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation
SemaCDR builds a unified semantic space with LLM-generated domain-agnostic features and adaptive fusion to improve cross-domain sequential recommendations over baselines.
-
From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation
LGCD creates pseudo-overlapping user data via LLM reasoning and uses conditional diffusion to generate target-domain user representations for inter-domain sequential recommendation without real overlapping users.
-
LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training
LLM-EDT improves cross-domain sequential recommendation by using LLMs for transferable item augmentation, dual-phase training to handle domain transitions, and domain-aware profiling to build user profiles.