一种超快的K-means用于向量嵌入索引
A Super Fast K-means for Indexing Vector Embeddings
AI总结：
SuperKMeans通过减少数据访问和计算开销，实现比FAISS和Scikit-Learn快7倍，比cuVS快4倍的高维向量嵌入聚类，同时保持检索质量。
摘要：
我们提出了SuperKMeans：一种用于聚类高维向量嵌入集合的k-means变种。SuperKMeans在现代CPU上比FAISS和Scikit-Learn快7倍，在GPU上比cuVS快4倍（图1），同时保持向量相似性搜索任务中聚类中心的质量。SuperKMeans的加速来自于通过可靠且高效地修剪不需要的维度来减少数据访问和计算开销。此外，我们提出了通过召回的早终止机制，该机制在迭代过程中当聚类中心的质量不再提升时提前终止k-means。在实践中，这进一步减少了运行时间而不影响检索质量。我们开源实现于https://github.com/cwida/SuperKMeans
英文摘要：
We present SuperKMeans: a k-means variant designed for clustering collections of high-dimensional vector embeddings. SuperKMeans' clustering is up to 7x faster than FAISS and Scikit-Learn on modern CPUs and up to 4x faster than cuVS on GPUs (Figure 1), while maintaining the quality of the resulting centroids for vector similarity search tasks. SuperKMeans acceleration comes from reducing data-access and compute overhead by reliably and efficiently pruning dimensions that are not needed to assign a vector to a centroid. Furthermore, we present Early Termination by Recall, a novel mechanism that early-terminates k-means when the quality of the centroids for retrieval tasks stops improving across iterations. In practice, this further reduces runtimes without compromising retrieval quality. We open-source our implementation at https://github.com/cwida/SuperKMeans
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
