Query-Aware Quantization for Maximum Inner Product Search

Authors

  • Jin Zhang University of Science and Technology of China
  • Defu Lian University of Science and Technology of China State Key Laboratory of Cognitive Intelligence, Hefei, China
  • Haodi Zhang Shenzhen University
  • Baoyun Wang Hisense
  • Enhong Chen University of Science and Technology of China State Key Laboratory of Cognitive Intelligence, Hefei, China

DOI:

https://doi.org/10.1609/aaai.v37i4.25613

Keywords:

DMKM: Web Search & Information Retrieval, DMKM: Web Personalization & User Modeling

Abstract

Maximum Inner Product Search (MIPS) plays an essential role in many applications ranging from information retrieval, recommender systems to natural language processing. However, exhaustive MIPS is often expensive and impractical when there are a large number of candidate items. The state-of-the-art quantization method of approximated MIPS is product quantization with a score-aware loss, developed by assuming that queries are uniformly distributed in the unit sphere. However, in real-world datasets, the above assumption about queries does not necessarily hold. To this end, we propose a quantization method based on the distribution of queries combined with sampled softmax. Further, we introduce a general framework encompassing the proposed method and multiple quantization methods, and we develop an effective optimization for the proposed general framework. The proposed method is evaluated on three real-world datasets. The experimental results show that it outperforms the state-of-the-art baselines.

Downloads

Published

2023-06-26

How to Cite

Zhang, J., Lian, D., Zhang, H., Wang, B., & Chen, E. (2023). Query-Aware Quantization for Maximum Inner Product Search. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4875-4883. https://doi.org/10.1609/aaai.v37i4.25613

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management