Skip to yearly menu bar Skip to main content


Talk
in
Competition: Practical Vector Search (Big ANN) Challenge 2023

[Streaming track] Puck : Efficient Multi-level Index Structure for Approximate Nearest Neighbor Search in Practice

Jie Yin


Abstract:

Puck proposes a multi-level index structure towards the ever growing datasets in practice. Two key methods, dynamic trimming and unifying PQ-table, are designed to accelerate training and search of multi-level quantization-based index. While maintaining a recall ratio >95% towards the SIFT10M dataset, a four-level quantization-based index achieves significantly better search throughput than Faiss-ivf and HNSW. The repository in GitHub is https://github.com/baidu/puck .

Authors: Jie Yin, Baidu Ben Huang, Baidu

Chat is not available.