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

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 e

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keyyin2025deg

Related papers

• Frequency-aware Graph Construction And Search For Dynamic Vector Databases (2025)0.00
• Efficient And Effective Retrieval Of Dense-sparse Hybrid Vectors Using Graph-based Approximate Nearest Neighbor Search (2024)0.00
• Fast Approximate Nearest Neighbor Search With A Dynamic Exploration Graph Using Continuous Refinement (2023)0.00
• HQANN: Efficient And Robust Similarity Search For Hybrid Queries With Structured And Unstructured Constraints (2022)9.76
• DGAI: Decoupled On-disk Graph-based ANN Index For Efficient Updates And Queries (2025)0.00
• Optimization Of Indexing Based On K-nearest Neighbor Graph For Proximity Search In High-dimensional Data (2018)0.00
• Navigable Proximity Graph-driven Native Hybrid Queries With Structured And Unstructured Constraints (2022)0.00
• Search Optimization With Query Likelihood Boosting And Two-level Approximate Search For Edge Devices (2023)0.00