Efficient Data Access Paths for Mixed Vector-Relational Search

arXiv:2403.15807v1 Announce Type: cross
Abstract: The rapid growth of machine learning capabilities and the adoption of data processing methods using vector embeddings sparked a great interest in creating systems for vector data management. While the predominant approach of vector data management is to use specialized index structures for fast search over the entirety of the vector embeddings, once combined with other (meta)data, the search queries can also become selective on relational attributes - typical for analytical queries. As using vector …

abstract adoption arxiv capabilities cs.ai cs.db cs.lg data data access data management data processing embeddings growth index machine machine learning management mixed processing relational search systems type vector vector embeddings