UMDA combines multi-objective learning with uncertainty modeling for RTA interception and applies distillation to enable single-pass aleatoric plus epistemic uncertainty with 10x inference speedup on JD and Criteo data.
Progressive layered extrac- tion (ple): A novel multi-task learning (mtl) model for personalized recommendations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Uncertainty Modeling for Multi-Objective RTA Interception with Distillation Acceleration
UMDA combines multi-objective learning with uncertainty modeling for RTA interception and applies distillation to enable single-pass aleatoric plus epistemic uncertainty with 10x inference speedup on JD and Criteo data.