SlimPer：使个性化模型变得精简且智能
SlimPer: Make Personalization Model Slim and Smart
- Meta Platforms, Inc.（Meta平台公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究针对工业推荐系统中Transformer架构的不足，提出SlimPer方法，将个性化排名重构成对紧凑知识库的迭代细化，可解耦模型深度与用户历史长度，统一多种特征并具可解释性，在Instagram相关业务上提升了用户参与度。
AI中文摘要：
Transformer 风格的架构越来越多地应用于工业推荐系统，但它们继承了与任务不匹配的设计前提：生成模型依赖于逐个令牌的自回归预测，这使得需要维护与序列长度成比例增长的大型中间张量。相比之下，推荐系统在没有令牌级监督的情况下为每个<用户，项目>对生成一组相关性分数。利用这一观察结果，我们提出了 SlimPer，它将个性化排名重新表述为对紧凑统一的<用户，项目>知识库的迭代细化。在每一层，模型选择性地查询原始多模态用户侧令牌，计算显式相关性匹配分数，并细化知识库，每层成本为 O(N)，中间表示固定大小。结果，模型深度与用户历史长度解耦，无需计算或内存成比例增长就能实现更深层次的相关性理解；仅请求优化通过在所有候选项目之间共享用户侧令牌的单个副本进一步减少内存。SlimPer 在单个主干中统一了稀疏、密集和序列特征，并通过其注意力机制提供了内在的可解释性。部署在 Instagram Reels 和 Feed 上，SlimPer 在提高用户参与度的同时简化了整个系统，并能够对 10k+细粒度用户历史事件进行有效建模。
英文摘要：
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 each <user, item> pair without token-level supervision. Leveraging this observation, we propose SlimPer, which reformulates personalized ranking as iterative refinement of a compact, unified <user, item> knowledge 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.
