Reconfigurable Inverted Index

TL;DR

The paper introduces Rii, a reconfigurable inverted index that improves subset search and dynamic updates in approximate nearest neighbor systems, maintaining high performance and flexibility.

Contribution

It proposes a data layout and system design that enable efficient subset search and dynamic updates in IVFADC-based systems.

Findings

Rii achieves comparable performance to Faiss.

Efficient subset search via linear PQ scan.

Maintains speed after adding new items.

Abstract

Existing approximate nearest neighbor search systems suffer from two fundamental problems that are of practical importance but have not received sufficient attention from the research community. First, although existing systems perform well for the whole database, it is difficult to run a search over a subset of the database. Second, there has been no discussion concerning the performance decrement after many items have been newly added to a system. We develop a reconfigurable inverted index (Rii) to resolve these two issues. Based on the standard IVFADC system, we design a data layout such that items are stored linearly. This enables us to efficiently run a subset search by switching the search method to a linear PQ scan if the size of a subset is small. Owing to the linear layout, the data structure can be dynamically adjusted after new items are added, maintaining the fast speed of the system. Extensive comparisons show that Rii achieves a comparable performance with state-of-the art systems such as Faiss.