Learned Metric Index — Proposition of learned indexing for unstructured data

作者:

Highlights:

• A novel approach for searching in unstructured data which exploits machine learning.

• Proposal interconnects learned models into a single index structure.

• Searching is re-framed as a classification problem instead of computing distances.

• The proof-of-concept implementation shows more than competitive performance.

• Numerous promising directions for the future enhancements are outlined.

摘要

•A novel approach for searching in unstructured data which exploits machine learning.•Proposal interconnects learned models into a single index structure.•Searching is re-framed as a classification problem instead of computing distances.•The proof-of-concept implementation shows more than competitive performance.•Numerous promising directions for the future enhancements are outlined.

论文关键词:Index structures,Learned index,Unstructured data,Content-based search,Metric space

论文评审过程:Received 5 March 2021, Revised 23 March 2021, Accepted 24 March 2021, Available online 8 April 2021, Version of Record 20 April 2021.

论文官网地址:https://doi.org/10.1016/j.is.2021.101774