Meta FAIR 发布 e-means：更快替代 mini-batch k-means 并入 FAISS 1.16.0
Meta FAIR Releases e-means: An Algorithm Beating k-means in 10x Fewer Epochs
Meta FAIR 把 e-means 塞进了 FAISS 1.16.0，跑聚类比 mini-batch k-means 快 10 到 45 倍，还不用加新超参数。做向量检索、RAG 索引的开发者升级一下就能省不少建索引的时间，接口不变直接换。
Meta FAIR 推出 e-means，作为 mini-batch k-means 的直接替代算法，已随 FAISS 1.16.0 发布。该算法以 Lloyd's k-means 的损失为基准：达到 Lloyd's 方法 25 个 epoch 的损失水平，只需 1.4 到 2.6 个 epoch。
在 GPU 上，e-means 相比传统 k-means 实现 10 到 45 倍的加速，且不引入任何新的超参数，开发者无需调参即可直接替换现有聚类流程。作为向量索引工具库 FAISS 的一部分，它主要服务于大规模向量检索场景中划分索引（如 IVF）所需的聚类预处理步骤。
对使用 FAISS 构建向量检索和 RAG 系统的团队而言，升级到 1.16.0 后可在不改变接口的情况下缩短索引构建时间。该算法属于经典聚类方法的工程改进，竞争对手主要是 HNSW 等图索引方案的上游构建环节，而非直接替代。
Meta FAIR Releases e-means: An Algorithm Beating k-means in 10x Fewer Epochs
Meta FAIR’s e-means is a mini-batch k-means replacement shipped in FAISS 1.16.0. It reaches Lloyd’s 25-epoch loss in 1.4 to 2.6 epochs, with 10-45x GPU speedups and no extra hyperparameters. The post Meta FAIR Releases e-means: An Algorithm Beating k-means in 10x Fewer Epochs appeared first on MarkTechPost .
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include FAISS, e-means, k-means, Meta.
Primary source verification: published directly by marktechpost with first-party authority.
