High-dimensional vector similarity search (HVSS) is gaining prominence as a powerful tool for various data science and AI applications. As vector data scales up, in-memory indexes pose a significant challenge due to the substantial increase in main memory requirements. A potential solution involves leveraging disk-based implementation, which stores and searches vector data on high-performance devices like NVMe SSDs. However, implementing HVSS for data segments proves to be intricate in vector databases where a single machine comprises multiple segments for system scalability. In this context, each segment operates with limited memory and disk space, necessitating a delicate balance between accuracy, efficiency, and space cost. Existing disk-based methods fall short as they do not holistically address all these requirements simultaneously. In this paper, we present Starling, an I/O-efficient disk-resident graph index framework that optimizes data layout and search strategy within the segment. It has two primary components: (1) a data layout incorporating an in-memory navigation graph and a reordered disk-based graph with enhanced locality, reducing the search path length and minimizing disk bandwidth wastage; and (2) a block search strategy designed to minimize costly disk I/O operations during vector query execution. Through extensive experiments, we validate the effectiveness, efficiency, and scalability of Starling. On a data segment with 2GB memory and 10GB disk capacity, Starling can accommodate up to 33 million vectors in 128 dimensions, offering HVSS with over 0.9 average precision and top-10 recall rate, and latency under 1 millisecond. The results showcase Starling's superior performance, exhibiting 43.9x higher throughput with 98% lower query latency compared to state-of-the-art methods while maintaining the same level of accuracy.

Vector databases have recently emerged as a hot topic in the field of databases, especially in industry. This is due to the widespread interest in Large Language Models (LLMs), where vector databases provide the relevant context for LLMs to produce more accurate responses. However, vector data is not new. It has been studied for more than two decades, leading to many efficient algorithms and indexes for vector similarity search. Thus, a natural question is: What is really new and what is next for vector databases? This panel will bring together several leading experts in vector databases to share their insights and experiences from various perspectives. The panel will also discuss the broader role of databases, beyond just vector databases, in the era of generative AI.

Approximate nearest neighbor (ANN) search in high-dimensional space plays an essential role in a variety of real-world applications. A well-known solution to ANN search, inverted file product quantization (IVFPQ) adopts inverted files to avoid exhaustive examination and compresses vectors using product quantization to reduce the space overhead. However, existing implementations use the same fixed probing cardinality (i.e., the number of cells to probe) setting for all queries, which leads to too many or too few cell examinations, thus increasing the average query latency or reducing the recall. To achieve a better trade-off between latency and accuracy, we enable probing cardinality estimation for high-dimensional ANN search by using deep learning techniques. We develop HBK-means, a hierarchical balanced clustering algorithm that reduces the data distribution imbalance of cells to enable a better estimation. Next, we develop PCE-Net, an encoder-decoder based neural network for estimating query-dependent minimum probing cardinality. In addition, we introduce two query optimization strategies: lower bound sorting based pruning (LBS-Pruning) and early termination (ET), to further reduce query latency. Extensive experiments with real-world data offer evidence that the proposed solution is capable of achieving better performance than IVFPQ and its variants.

Maximum inner product search (MIPS) in high-dimensional spaces has wide applications but is computationally expensive due to the curse of dimensionality. Existing studies employ asymmetric transformations that reduce the MIPS problem to a nearest neighbor search (NNS) problem, which can be solved using locality-sensitive hashing (LSH). However, these studies usually maintain multiple hash tables and locally examine them one by one, which may cause additional costs on probing unnecessary points. In addition, LSH is applied without taking into account the properties of the inner product. In this paper, we develop a fast search framework FARGO for MIPS on large-scale, high-dimensional data. We propose a global multi-probing (GMP) strategy that exploits the properties of the inner product to globally examine high quality candidates. In addition, we develop two optimization techniques. First, different with existing transformations that introduce either distortion errors or data distribution imbalances, we design a novel transformation, called random XBOX transformation, that avoids the negative effects of data distribution imbalances. Second, we propose a global adaptive early termination condition that finds results quickly and offers theoretical guarantees. We conduct extensive experiments with real-world data that offer evidence that FARGO is capable of outperforming existing proposals in terms of both accuracy and efficiency.

With the development of learning-based embedding models, embedding vectors are widely used for analyzing and searching unstructured data. As vector collections exceed billion-scale, fully managed and horizontally scalable vector databases are necessary. In the past three years, through interaction with our 1200+ industry users, we have sketched a vision for the features that next-generation vector databases should have, which include long-term evolvability, tunable consistency, good elasticity, and high performance. We present Manu, a cloud native vector database that implements these features. It is difficult to integrate all these features if we follow traditional DBMS design rules. As most vector data applications do not require complex data models and strong data consistency, our design philosophy is to relax the data model and consistency constraints in exchange for the aforementioned features. Specifically, Manu firstly exposes the write-ahead log (WAL) and binlog as backbone services. Secondly, write components are designed as log publishers while all read-only analytic and search components are designed as independent subscribers to the log services. Finally, we utilize multi-version concurrency control (MVCC) and a delta consistency model to simplify the communication and cooperation among the system components. These designs achieve a low coupling among the system components, which is essential for elasticity and evolution. We also extensively optimize Manu for performance and usability with hardware-aware implementations and support for complex search semantics. Manu has been used for many applications, including, but not limited to, recommendation, multimedia, language, medicine and security. We evaluated Manu in three typical application scenarios to demonstrate its efficiency, elasticity, and scalability.

Recently, there has been a pressing need to manage high-dimensional vector data in data science and AI applications. This trend is fueled by the proliferation of unstructured data and machine learning (ML), where ML models usually transform unstructured data into feature vectors for data analytics, e.g., product recommendation. Existing systems and algorithms for managing vector data have two limitations: (1) They incur serious performance issue when handling large-scale and dynamic vector data; and (2) They provide limited functionalities that cannot meet the requirements of versatile applications.