苹果用 SupportNet 学习更快的 MIPS 检索路由
苹果研究人员在 ICML 2026 展示的论文中介绍 SupportNet:针对固定的键值数据库离线训练小型神经网络,将查询更快地路由至最佳匹配键。苹果将 Natural Questions 划分为 128 个簇的测试中,小模型以 1.74 毫秒达到 95% 的路由召回率,而质心路由为 3.36 毫秒;大模型同样以 1.74 毫秒达到 97%。这些数据来自苹果公布的评估。
结果显示,当查询分布已知时,学习路由可降低查询路由延迟。与质心路由相比,SupportNet 将部分成本转移到前期离线训练,以换取快速、轻量的推理。
content type highlightpublished November 5, 2026
Faster Retrieval for Better, More Efficient RAG
Maximum inner product search (MIPS) sits at the core of recommendation systems, search, and retrieval-augmented generation (RAG). Given a query vector, MIPS systems search within a database of millions of candidate key vectors for the one that best matches the query. The original data point associated with that best-matching key is then used to handle the query: in RAG, the document that is best suited to answer the question is typically prefixed to the query.
As the number of keys grows to millions and vector dimensions reach thousands, the computational cost of running an exhaustive comparison of the query to all keys grows dramatically. Numerous approximate methods have been proposed to trade off accuracy for speed using clustering and quantization. While these baseline methods focus on the properties of the set of keys to build up clever indexing structures, their geometric arguments loosely assume that the set of queries itself will resemble that found in keys, or bypass any considerations about what the queries will look like. This can be problematic on two fronts: In the crucial RAG case, queries arise from short user-generated questions, whereas keys represent long, informative, and curated pieces of text, making keys and queries substantially different. Additionally, most MIPS use cases deployed in production target an existing base of users with a stable, well-characterized query distribution — a signal that generic, query-agnostic methods leave untapped. Crafting methods that work best for a likely source of inputs — rather than aiming for good performance on all possible inputs — is a central tenet of modern machine learning that helps redirect compute resources more efficiently.