Papers and citations

Research behind RaBitQ-Library's quantization and graph-search implementations. If you use this work, please cite the papers relevant to the method you use.

Original RaBitQ

The one-bit method and its theoretical error bound.

Jianyang Gao and Cheng Long. “RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search.” Proceedings of the ACM on Management of Data 2, 3, Article 167 (May 2024), 27 pages. https://doi.org/10.1145/3654970.

Multi-bit RaBitQ

Practical multi-bit quantization and asymptotically optimal error guarantees.

Jianyang Gao, Yutong Gou, Yuexuan Xu, Yongyi Yang, Cheng Long, and Raymond Chi-Wing Wong. “Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search.” Proceedings of the ACM on Management of Data 3, 3, Article 202 (June 2025), 26 pages. https://doi.org/10.1145/3725413.

SymphonyQG

Integration of quantization and graph search. The paper uses raw vectors for candidate scoring; the library's optional 4/8-bit storage and PiPNN initialization are implementation extensions. See the SymphonyQG guide.

Yutong Gou, Jianyang Gao, Yuexuan Xu, and Cheng Long. “SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search.” Proceedings of the ACM on Management of Data 3, 1, Article 80 (February 2025), 26 pages. https://doi.org/10.1145/3709730.