Approximate Nearest Neighbor Search With Window Filters

Engels Joshua, Landrum Benjamin, Yu Shangdi, Dhulipala Laxman, Shun Julian. Arxiv 2024

[Paper]    
ARXIV Independent

We define and investigate the problem of $\mathit{\text{c-approximate windowsearch}}$: approximate nearest neighbor search where each point in the dataset has a numeric label, and the goal is to find nearest neighbors to queries within arbitrary label ranges. Many semantic search problems, such as image and document search with timestamp filters, or product search with cost filters, are natural examples of this problem. We propose and theoretically analyze a modular tree-based framework for transforming an index that solves the traditional c-approximate nearest neighbor problem into a data structure that solves window search. On standard nearest neighbor benchmark datasets equipped with random label values, adversarially constructed embeddings, and image search embeddings with real timestamps, we obtain up to a $75\times$ speedup over existing solutions at the same level of recall.

Similar Work

• Exploiting Spatial Overlap To Efficiently Compute Appearance Distances Between Image Windows
• Subspace Approximation For Approximate Nearest Neighbor Search In NLP
• EFANNA An Extremely Fast Approximate Nearest Neighbor Search Algorithm Based On Knn Graph
• LANNS A Web-scale Approximate Nearest Neighbor Lookup System