用聚类压缩向量，存一半数据性能几乎不降。
Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
- 用聚类合并相似词向量，减少存储量
- 索引体积减半，性能损失小于1%
- 无需改架构，可直接替换现有流程
近年来，以ColBERT为代表的多向量检索方法在神经信息检索领域日益流行。通过存储词级表示而非文档级表示，这类方法在跨域场景下表现出优异的检索性能。然而，需存储大量向量带来的存储与内存开销仍是主要瓶颈。本文提出一种基于聚类的词向量池化方法，可大幅减少需存储的向量数量。该方法使ColBERT索引的存储与内存占用降低50%，性能几乎无损；进一步压缩可实现66%至75%的向量减少，多数数据集上性能下降仍低于5%。该方法无需架构改动或查询时计算，可作为简单插件在任意类似ColBERT的模型索引阶段使用。
原文摘要 · Abstract (English)
Over the last few years, multi-vector retrieval methods, spearheaded by ColBERT, have become an increasingly popular approach to Neural IR. By storing representations at the token level rather than at the document level, these methods have demonstrated very strong retrieval performance, especially in out-of-domain settings. However, the storage and memory requirements necessary to store the large number of associated vectors remain an important drawback, hindering practical adoption. In this paper, we introduce a simple clustering-based token pooling approach to aggressively reduce the number of vectors that need to be stored. This method can reduce the space & memory footprint of ColBERT indexes by 50% with virtually no retrieval performance degradation. This method also allows for further reductions, reducing the vector count by 66%-to-75% , with degradation remaining below 5% on a vast majority of datasets. Importantly, this approach requires no architectural change nor query-time processing, and can be used as a simple drop-in during indexation with any ColBERT-like model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。