RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems
For industrial recommender systems, RankUp provides a practical solution to improve representation capacity and revenue, though it is an incremental improvement over existing architectures.
RankUp addresses representation collapse in deep recommender systems by introducing randomized permutation splitting and multi-embedding, achieving GMV improvements of 3.41%, 4.81%, and 2.21% in large-scale production across Weixin platforms.
The scaling laws for recommender systems have been increasingly validated, where MetaFormer-based architectures consistently benefit from increased model depth, hidden dimensionality, and user behavior sequence length. However, whether representation capacity scales proportionally with parameter growth remains largely unexplored. Prior studies on RankMixer reveal that the effective rank of token representations exhibits a damped oscillatory trajectory across layers, failing to increase consistently with depth and even degrading in deeper layers. Motivated by this observation, we propose \textbf{RankUp}, an architecture designed to mitigate representation collapse and enhance expressive capacity through randomized permutation splitting over sparse features, a multi-embedding paradigm, global token integration, crossed pretrained embedding tokens and task-specific token decoupling. RankUp has been fully deployed in large-scale production across Weixin Video Accounts, Official Accounts and Moments, yielding GMV improvements of 3.41\%, 4.81\% and 2.21\%, respectively.