Approximate Nearest Neighbor Search in High Dimensional Vector Databases: Current Research and Future Directions

Approximate nearest neighbor search is an important research topic with a wide range of applications. In this study, we first introduce the problem and review major research results in the past. We then discuss the current work in the database research community, categorizing the work by their key underlying methodologies, such as locality-sensitive hashing, product quantization, and approximate nearest neighbor graphs. Finally, we examine several new directions, with a focus on vector databases to support large language models.