High-dimensional Approximate Nearest Neighbor Search: With Reliable And Efficient Distance Comparison Operations

Abstract

Approximate K nearest neighbor (AKNN) search is a fundamental and challenging problem. We observe that in high-dimensional space, the time consumption of nearly all AKNN algorithms is dominated by that of the distance comparison operations (DCOs). For each operation, it scans full dimensions of an object and thus, runs in linear time wrt the dimensionality. To speed it up, we propose a randomized algorithm named ADSampling which runs in logarithmic time wrt to the dimensionality for the majority of DCOs and succeeds with high probability. In addition, based on ADSampling we develop one general and two algorithm-specific techniques as plugins to enhance existing AKNN algorithms. Both theoretical and empirical studies confirm that: (1) our techniques introduce nearly no accuracy loss and (2) they consistently improve the efficiency.

Stats

• citations61
• S2 citations—
• github stars0
• HF likes0
• heat score13.44
• arxiv keygao2023high

Related papers

• Effective And General Distance Computation For Approximate Nearest Neighbor Search (2024)5.84
• Efficient Data-aware Distance Comparison Operations For High-dimensional Approximate Nearest Neighbor Search (2024)5.24
• Adaptive Estimation For Approximate K-nearest-neighbor Computations (2019)0.00
• Hd-index: Pushing The Scalability-accuracy Boundary For Approximate Knn Search In High-dimensional Spaces (2018)14.02
• Let Them Have CAKES: A Cutting-edge Algorithm For Scalable, Efficient, And Exact Search On Big Data (2023)2.68
• Dimensionality-reduction Techniques For Approximate Nearest Neighbor Search: A Survey And Evaluation (2024)0.00
• Efficient Autotuning Of Hyperparameters In Approximate Nearest Neighbor Search (2018)6.77
• Quantization Meets Projection: A Happy Marriage For Approximate K-nearest Neighbor Search (2024)0.00