A three-stage MoE variant of MLoRA improves multi-domain CTR prediction on sparse Taobao data but not on denser Movielens splits.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
A three-stage MoE variant of MLoRA improves multi-domain CTR prediction on sparse Taobao data but not on denser Movielens splits.