Search papers, labs, and topics across Lattice.
This paper introduces SlimPer, a novel approach to personalized ranking in recommendation systems that reformulates the traditional autoregressive prediction method used in generative models. By leveraging a compact knowledge base and an iterative refinement process, SlimPer achieves efficient relevance scoring with a fixed-size representation, allowing for deeper model architectures without the typical increase in computational costs. The method was successfully deployed on Instagram Reels and Feed, resulting in significant improvements in user engagement while optimizing memory usage and interpretability.
SlimPer achieves deeper relevance understanding in recommendation systems without the computational bloat, leading to measurable boosts in user engagement on platforms like Instagram.
Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length. In contrast, recommendation systems produce a single set of relevance scores for eachpair without token-level supervision. Leveraging this observation, we propose SlimPer, which reformulates personalized ranking as iterative refinement of a compact, unifiedknowledge base. At each layer, the model selectively queries raw multi-modal user-side tokens, computes explicit relevance matching scores, and refines the knowledge base, all in O(N) per-layer cost with a fixed-size intermediate representation. As a result, model depth is decoupled from user history length, enabling deeper relevance understanding without proportional growth in compute or memory; request-only optimization further trims memory by sharing a single copy of user-side tokens across all candidate items. SlimPer unifies sparse, dense, and sequence features within a single backbone and provides inherent interpretability through its attention mechanism. Deployed on Instagram Reels and Feed, SlimPer yields measurable improvements in user engagement while streamlining the overall system and enabling effective modeling of 10k+ fine-grained user history events.
