real-world datasets real-world-datasets Leaderboard
Auto-discovered from papers reporting real-world datasets (speedup). · Metric: speedup (higher is better)
| # | Model | speedup | Paper |
|---|---|---|---|
| 1 | TaCo: Data-adaptive and Query-aware Subspace Collision for High-dimensional Approximate Nearest Neighbor Search | 8.00 | — |
| 2 | VSAG: An Optimized Search Framework for Graph-based Approximate Nearest Neighbor Search | 4.00 | — |
| 3 | BBC: Improving Large-k Approximate Nearest Neighbor Search with a Bucket-based Result Collector | 3.80 | — |
| 4 | Fast Tuning the Index Construction Parameters of Proximity Graphs in Vector Databases | 2.37 | — |
| 5 | Dynamically Detect and Fix Hardness for Efficient Approximate Nearest Neighbor Search | 2.35 | — |
| 6 | Frequency-Aware Graph Construction and Search for Dynamic Vector Databases | 2.00 | — |
| 7 | Effective and General Distance Computation for Approximate Nearest Neighbor Search | 1.60 | — |
| 8 | Scalable Graph Indexing using GPUs for Approximate Nearest Neighbor Search | 1.32 | — |