Vector search using method of clustering using ensemble of oblivious trees

Information retrieval using machine learning algorithms is based on transforming the original multimodal documents into vector representations. These vectors are then indexed, and the search is performed within this index. A popular method for indexing is vector clustering such as with k-nearest neighbors. We propose a clustering method based on an ensemble of Oblivious Decision Trees and introduce a vector search algorithm built on this method. The proposed clustering method is deterministic and supports parameter serialization for the ensemble. The essence of the method involves training an ensemble of binary or ternary Oblivious Trees. This ensemble is then used to compute a hash for each of the original vectors. Vectors with the same hash are considered to belong to the same cluster. For searching, several clusters are selected whose centroids are closest to the vector representation of the search query followed by a full search of the vector representations within the selected clusters. The proposed method demonstrates search quality comparable to widely used industry-standard vector search libraries, such as Faiss, Annoy, and HNSWlib. For datasets with an angular distance metric, the proposed search method achieves accuracy equal to or better than existing solutions. For datasets with a Euclidean distance metric, the search quality is on par with existing solutions. The developed method can be applied to improve search quality in the development of multimodal search systems. The ability to serialize enables clustering data on one computational node and transferring ensemble parameters to another, allowing the proposed algorithm to be utilized in distributed systems.