PRIME: Mitigating Subgroup Optimization Competition in Shared CTR Top Networks with Plug-in Residual Input-Conditioned Mixture of Expert
Results show that function-preserving conditional residuals add input-dependent capacity while preserving the Dense path and its optimization stability, and introduce PRIME (Plug-in Residual Input-conditioned Mixture of Experts), a Dense-anchored mixture of low-rank residual experts.
Heng Yao, Si-Yun Hou, Tian-Ying Liu et al.
· 0 citations