Book
Open access
Jul 2026
DPEO: Dynamic Preference Evolution Optimization for Self-Evolving CTR Prediction
This paper proposes DPEO (Dynamic Preference Evolution Optimization), a co-evolutionary framework that transforms CTR modeling into a dynamic policy contention task, enabling the sub-learners to serve as alternating evolutionary benchmarks and 'self-evolve' toward the global optimum.
Kun Yao, Congcong Liu, Ziheng Ni et al.
· Annual International ACM SIG... · 0 citations