DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph

TL;DR

This paper introduces DEG, a novel graph-based index for hybrid vector search that efficiently adapts to changing query parameters, significantly improving performance for bimodal data retrieval.

Contribution

DEG is the first index to dynamically adapt to varying $oldsymbol{ extalpha}$ values in hybrid vector search, combining novel algorithms for neighbor candidate selection, edge pruning, and acceleration.

Findings

DEG outperforms existing methods across multiple datasets.

It maintains high accuracy with reduced query time.

The approach effectively handles dynamic $oldsymbol{ extalpha}$ scenarios.

Abstract

Bimodal data, such as image-text pairs, has become increasingly prevalent in the digital era. The Hybrid Vector Query (HVQ) is an effective approach for querying such data and has recently garnered considerable attention from researchers. It calculates similarity scores for objects represented by two vectors using a weighted sum of each individual vector's similarity, with a query-specific parameter $\alpha$ to determine the weight. Existing methods for HVQ typically construct Approximate Nearest Neighbors Search (ANNS) indexes with a fixed $\alpha$ value. This leads to significant performance degradation when the query's $\alpha$ dynamically changes based on the different scenarios and needs. In this study, we introduce the Dynamic Edge Navigation Graph (DEG), a graph-based ANNS index that maintains efficiency and accuracy with changing $\alpha$ values. It includes three novel components: (1) a greedy Pareto frontier search algorithm to compute a candidate neighbor set for each node, which comprises the node's approximate nearest neighbors for all possible $\alpha$ values; (2) a dynamic edge pruning strategy to determine the final edges from the candidate set and assign each edge an active range. This active range enables the dynamic use of the Relative Neighborhood Graph's pruning strategy based on the query's $\alpha$ values, skipping redundant edges at query time and achieving a better accuracy-efficiency trade-off; and (3) an edge seed method that accelerates the querying process. Extensive experiments on real-world datasets show that DEG demonstrates superior performance compared to existing methods under varying $\alpha$ values.