Empowering Graph-based Approximate Nearest Neighbor Search with Adaptive Awareness Capabilities

2025-06-19

AI Summary

To address local optima, computational redundancy, and query-data distribution mismatch in graph-based approximate nearest neighbor search (ANNS) indexing, this paper proposes GATE—a lightweight adaptive module. GATE’s core innovation lies in the first joint modeling of graph topology and query semantics: it dynamically optimizes entry points via hub node selection and high-dimensional cluster structure analysis; introduces a learnable navigation subgraph for low-overhead online inference; and employs contrastive learning with dual-tower encoding to align query and data distributions. Crucially, GATE requires no graph reconstruction and maintains controllable memory overhead. Evaluated on mainstream benchmarks, it achieves 1.2–2.0× speedup in query latency over state-of-the-art graph ANNS methods while exhibiting lower inference latency.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Distributed Search
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Approximate Nearest Neighbor Search (ANNS) in high-dimensional spaces finds extensive applications in databases, information retrieval, recommender systems, etc. While graph-based methods have emerged as the leading solution for ANNS due to their superior query performance, they still face several challenges, such as struggling with local optima and redundant computations. These issues arise because existing methods (i) fail to fully exploit the topological information underlying the proximity graph G, and (ii) suffer from severe distribution mismatches between the base data and queries in practice. To this end, this paper proposes GATE, high-tier proximity Graph with Adaptive Topology and Query AwarEness, as a lightweight and adaptive module atop the graph-based indexes to accelerate ANNS. Specifically, GATE formulates the critical problem to identify an optimal entry point in the proximity graph for a given query, facilitating faster online search. By leveraging the inherent clusterability of high-dimensional data, GATE first extracts a small set of hub nodes V as candidate entry points. Then, resorting to a contrastive learning-based two-tower model, GATE encodes both the structural semantics underlying G and the query-relevant features into the latent representations of these hub nodes V. A navigation graph index on V is further constructed to minimize the model inference overhead. Extensive experiments demonstrate that GATE achieves a 1.2-2.0X speed-up in query performance compared to state-of-the-art graph-based indexes.

Problem

• Improves graph-based ANNS by addressing local optima issues
• Reduces redundant computations in high-dimensional nearest neighbor search
• Enhances query performance via adaptive topology and awareness

Innovation

• Adaptive topology for optimal entry points
• Contrastive learning-based two-tower model
• Navigation graph index minimizes inference overhead