When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression

Title:When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression

Abstract:Recent high-performing text embedding models often produce high-dimensional real-valued vectors, resulting in substantial storage and computational costs. To address this issue, embedding compression methods based on dimensionality reduction or quantization have been proposed; however, the effects of their combination have not been sufficiently investigated. In this paper, we systematically investigate how dimensionality reduction and quantization jointly affect embedding compression across four task families in the Massive Text Embedding Benchmark (MTEB), using five pretrained embedding models. Our results show that combining dimensionality reduction and quantization can preserve near-original performance with substantially smaller storage footprints than either method alone. In particular, for classification, several models retain at least 99% of their original classification score using less than 0.1% of the storage required by the original embeddings. The preferred balance between dimensionality and bit-width varies across tasks, with retrieval generally being more sensitive to compression.

Computation and Language (cs.CL)

arXiv:2606.01074 [cs.CL]

(or arXiv:2606.01074v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.01074 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.