Large-scale Graph Building In Dynamic Environments: Low Latency And High Quality

Abstract

Learning and constructing large-scale graphs has attracted attention in recent decades, resulting in a rich literature that introduced various systems, tools, and algorithms. Grale is one of such tools that is designed for offline environments and is deployed in more than 50 different industrial settings at Google. Grale is widely applicable because of its ability to efficiently learn and construct a graph on datasets with multiple types of features. However, it is often the case that applications require the underlying data to evolve continuously and rapidly and the updated graph needs to be available with low latency. Such setting make the use of Grale prohibitive. While there are Approximate Nearest Neighbor (ANN) systems that handle dynamic updates with low latency, they are mostly limited to similarities over a single embedding. In this work, we introduce a system that inherits the advantages and the quality of Grale, and maintains a graph construction in a dynamic setting with

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydealmeida2025large

Related papers

• Grale: Designing Networks For Graph Learning (2020)10.85
• CAGRA: Highly Parallel Graph Construction And Approximate Nearest Neighbor Search For Gpus (2023)12.17
• Approximate K-nn Graph Construction: A Generic Online Approach (2018)11.08
• Fast Approximate Nearest Neighbor Search With A Dynamic Exploration Graph Using Continuous Refinement (2023)0.00
• Large Scale Graph Learning From Smooth Signals (2017)0.00
• Parlayann: Scalable And Deterministic Parallel Graph-based Approximate Nearest Neighbor Search Algorithms (2023)10.35
• Stars: Tera-scale Graph Building For Clustering And Graph Learning (2022)0.00
• DGAI: Decoupled On-disk Graph-based ANN Index For Efficient Updates And Queries (2025)0.00