From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendation Models
This work proposes CRAFT, a Contextual Residual Adaptive Feature Transport block, which summarizes non-sequential features into a reliability-aware contextual field and uses it to generate residual displacement and memory-preserving signals for intent and sequence representations.
Zi-Chen Luo, Jiaqi Guo, Ke-Ming Gu et al.
· 0 citations