Unstructured data (e.g., video or text) is now commonly queried by using computationally expensive deep neural networks or human labelers to produce structured information, e.g., object types and positions in video. To accelerate queries, many recent systems (e.g., BlazeIt, NoScope, Tahoma, SUPG, etc.) train a query-specific proxy model to approximate a large target labelers (i.e., these expensive neural networks or human labelers). These models return proxy scores that are then used in query processing algorithms. Unfortunately, proxy models usually have to be trained per query and require large amounts of annotations from the target labelers.
In this work, we develop an index (trainable semantic index, TASTI) that simultaneously removes the need for per-query proxies and is more efficient to construct than prior indexes. TASTI accomplishes this by leveraging semantic similarity across records in a given dataset. Specifically, it produces embeddings for each record such that records with close embeddings have similar target labeler outputs. TASTI then generates high-quality proxy scores via embeddings without needing to train a per-query proxy. These scores can be used in existing proxy-based query processing algorithms (e.g., for aggregation, selection, etc.). We theoretically analyze TASTI and show that a low embedding training error guarantees downstream query accuracy for a natural class of queries. We evaluate TASTI on five video, text, and speech datasets, and three query types. We show that TASTI's indexes can be 10$\times$ less expensive to construct than generating annotations for current proxy-based methods, and accelerate queries by up to 24$\times$.
A major problem of unstructured P2P systems is their heavy network traffic. This is caused mainly by high numbers of query answers, many of which are irrelevant for users. One solution to this problem is to use Top-k queries whereby the user can specify a limited number (k) of the most relevant answers. In this paper, we present FD, a (Fully Distributed) framework for executing Top-k queries in unstructured P2P systems, with the objective of reducing network traffic. FD consists of a family of algorithms that are simple but effec-tive. FD is completely distributed, does not depend on the exist…
Indexing large-scale databases in main memory is still challenging today. Learned index structures -- in which the core components of classical indexes are replaced with machine learning models -- have recently been suggested to significantly improve performance for read-only range queries. However, a recent benchmark study shows that learned indexes only achieve limited performance improvements for real-world data on modern hardware. More specifically, a learned model cannot learn the micro-level details and fluctuations of data distributions thus resulting in poor accuracy; or it can fit to …
The queries defined on data warehouses are complex and use several join operations that induce an expensive computational cost. This cost becomes even more prohibitive when queries access very large volumes of data. To improve response time, data warehouse administrators generally use indexing techniques such as star join indexes or bitmap join indexes. This task is nevertheless complex and fastidious. Our solution lies in the field of data warehouse auto-administration. In this framework, we propose an automatic index selection strategy. We exploit a data mining technique ; more precisely fre…
One of the major challenges being faced by Database managers today is to manage the performance of complex SQL queries which are dynamic in nature. Since it is not possible to tune each and every query because of its dynamic nature, there is a definite possibility that these queries may cause serious database performance issues if left alone. Conventional indexes are useful only for those queries which are frequently executed or those columns which are frequently joined in SQL queries. This proposal is regarding a method, a query optimizer for optimizing database queries in a database manageme…
We study the problem of answering k-hop reachability queries in a directed graph, i.e., whether there exists a directed path of length k, from a source query vertex to a target query vertex in the input graph. The problem of k-hop reachability is a general problem of the classic reachability (where k=infinity). Existing indexes for processing classic reachability queries, as well as for processing shortest path queries, are not applicable or not efficient for processing k-hop reachability queries. We propose an index for processing k-hop reachability queries, which is simple in design and effi…
The in-memory approximate nearest neighbor search (ANNS) algorithms have achieved great success for fast high-recall query processing, but are extremely inefficient when handling hybrid queries with unstructured (i.e., feature vectors) and structured (i.e., related attributes) constraints. In this paper, we present HQANN, a simple yet highly efficient hybrid query processing framework which can be easily embedded into existing proximity graph-based ANNS algorithms. We guarantee both low latency and high recall by leveraging navigation sense among attributes and fusing vector similarity search …
Bitmap indexes are routinely used to speed up simple aggregate queries in databases. Set operations such as intersections, unions and complements can be represented as logical operations (AND, OR, NOT). However, less is known about the application of bitmap indexes to more advanced queries. We want to extend the applicability of bitmap indexes. As a starting point, we consider symmetric Boolean queries (e.g., threshold functions). For example, we might consider stores as sets of products, and ask for products that are on sale in 2 to 10 stores. Such symmetric Boolean queries generalize interse…
Indoor location-based services (LBS), such as POI search and routing, are often built on top of typical indoor spatial queries. To support such queries and indoor LBS, multiple techniques including model/indexes and search algorithms have been proposed. In this work, we conduct an extensive experimental study on existing proposals for indoor spatial queries. We survey five model/indexes, compare their algorithmic characteristics, and analyze their space and time complexities. We also design an in-depth benchmark with real and synthetic datasets, evaluation tasks and performance metrics. Enable…
Database systems analyze queries to determine upfront which data is needed for answering them and use indexes and other physical design techniques to speed-up access to that data. However, for important classes of queries, e.g., HAVING and top-k queries, it is impossible to determine up-front what data is relevant. To overcome this limitation, we develop provenance-based data skipping (PBDS), a novel approach that generates provenance sketches to concisely encode what data is relevant for a query. Once a provenance sketch has been captured it is used to speed up subsequent queries. PBDS can ex…
Compressed bitmap indexes are used to speed up simple aggregate queries in databases. Indeed, set operations like intersections, unions and complements can be represented as logical operations (AND,OR,NOT) that are ideally suited for bitmaps. However, it is less obvious how to apply bitmaps to more advanced queries. For example, we might seek products in a store that meet some, but maybe not all, criteria. Such threshold queries generalize intersections and unions; they are often used in information-retrieval and data-mining applications. We introduce new algorithms that are sometimes three or…
A large fraction of an XML document typically consists of text data. The XPath query language allows text search via the equal, contains, and starts-with predicates. Such predicates can efficiently be implemented using a compressed self-index of the document's text nodes. Most queries, however, contain some parts of querying the text of the document, plus some parts of querying the tree structure. It is therefore a challenge to choose an appropriate evaluation order for a given query, which optimally leverages the execution speeds of the text and tree indexes. Here the SXSI system is introduce…
Many applications need to process massive streams of spatio-textual data in real-time against continuous spatio-textual queries. For example, in location-aware ad targeting publish/subscribe systems, it is required to disseminate millions of ads and promotions to millions of users based on the locations and textual profiles of users. In this paper, we study indexing of continuous spatio-textual queries. There exist several related spatio-textual indexes that typically integrate a spatial index with a textual index. However, these indexes usually have a high demand for main-memory and assume th…
Databases employ indexes to filter out irrelevant records, which reduces scan overhead and speeds up query execution. However, this optimization is only available to queries that filter on the indexed attribute. To extend these speedups to queries on other attributes, database systems have turned to secondary and multi-dimensional indexes. Unfortunately, these approaches are restrictive: secondary indexes have a large memory footprint and can only speed up queries that access a small number of records, and multi-dimensional indexes cannot scale to more than a handful of columns. We present Cor…
Commercial off-the-shelf DataBase Management Systems (DBMSes) are highly optimized to process a wide range of queries by means of carefully designed indexing and query planning. However, many aggregate range queries are usually performed by DBMSes using sequential scans, and certain needs, like storing Authenticated Data Structures (ADS), are not supported at all. Theoretically, these needs could be efficiently fulfilled adopting specific kinds of indexing, which however are normally ruled-out in DBMSes design. We introduce the concept of overlay index: an index that is meant to be stored in a…
XML document markup is highly repetitive and therefore well compressible using dictionary-based methods such as DAGs or grammars. In the context of selectivity estimation, grammar-compressed trees were used before as synopsis for structural XPath queries. Here a fully-fledged index over such grammars is presented. The index allows to execute arbitrary tree algorithms with a slow-down that is comparable to the space improvement. More interestingly, certain algorithms execute much faster over the index (because no decompression occurs). E.g., for structural XPath count queries, evaluating over t…
Database administrators construct secondary indexes on data tables to accelerate query processing in relational database management systems (RDBMSs). These indexes are built on top of the most frequently queried columns according to the data statistics. Unfortunately, maintaining multiple secondary indexes in the same database can be extremely space consuming, causing significant performance degradation due to the potential exhaustion of memory space. In this paper, we demonstrate that there exist many opportunities to exploit column correlations for accelerating data access. We propose HERMIT…
Data skipping reduces I/O for SQL queries by skipping over irrelevant data objects (files) based on their metadata. We extend this notion by allowing developers to define their own data skipping metadata types and indexes using a flexible API. Our framework is the first to natively support data skipping for arbitrary data types (e.g. geospatial, logs) and queries with User Defined Functions (UDFs). We integrated our framework with Apache Spark and it is now deployed across multiple products/services at IBM. We present our extensible data skipping APIs, discuss index design, and implement vario…
A corpus of recent work has revealed that the learned index can improve query performance while reducing the storage overhead. It potentially offers an opportunity to address the spatial query processing challenges caused by the surge in location-based services. Although several learned indexes have been proposed to process spatial data, the main idea behind these approaches is to utilize the existing one-dimensional learned models, which requires either converting the spatial data into one-dimensional data or applying the learned model on individual dimensions separately. As a result, these a…
As research interest surges, vector similarity search is applied in multiple fields, including data mining, computer vision, and information retrieval. {Given a set of objects (e.g., a set of images) and a query object, we can easily transform each object into a feature vector and apply the vector similarity search to retrieve the most similar objects. However, the original vector similarity search cannot well support \textit{hybrid queries}, where users not only input unstructured query constraint (i.e., the feature vector of query object) but also structured query constraint (i.e., the desir…
Multi-criteria decision making has been made possible with the advent of skyline queries. However, processing such queries for high dimensional datasets remains a time consuming task. Real-time applications are thus infeasible, especially for non-indexed skyline techniques where the datasets arrive online. In this paper, we propose a caching mechanism that uses the semantics of previous skyline queries to improve the processing time of a new query. In addition to exact queries, utilizing such special semantics allow accelerating related queries. We achieve this by generating partial result set…
Using structural informations to summarize graph-structured RDF data is helpful in tackling query performance issues. However, leveraging structural indexes needs to revise or even redesign the internal of RDF systems. Given an RDF dataset that have already been bulk loaded into a relational RDF system, we aim at improving the query performance on such systems. We do so by summarizing neighborhood structures and encoding them into triples which can be managed along side the exist instance data. At query time, we optimally select the effective structural patterns, and adding these patterns to t…
Spatial data is ubiquitous. Massive amounts of data are generated every day from billions of GPS-enabled devices such as cell phones, cars, sensors, and various consumer-based applications such as Uber, Tinder, location-tagged posts in Facebook, Twitter, Instagram, etc. This exponential growth in spatial data has led the research community to focus on building systems and applications that can process spatial data efficiently. In the meantime, recent research has introduced learned index structures. In this work, we use techniques proposed from a state-of-the art learned multi-dimensional inde…
Unstructured data(e.g., images, videos, PDF files, etc.) contain semantic information, for example, the facial feature of a person and the plate number of a vehicle. There could be semantic relationships between data items which are not explicitly represented. For example, a person's face may appear in two irrelevant photos. Also, much information is represented as structured data(e.g., the person's name and age). End-users prefer to query the semantic information from unstructured data together with structured data based on the potential relationships among them. However, due to the lack of a…
In this work we explore the use of metric index structures, which accelerate nearest neighbor queries, in the scenario where we need to interleave insertions and queries during deployment. This use-case is inspired by a real-life need in malware analysis triage, and is surprisingly understudied. Existing literature tends to either focus on only final query efficiency, often does not support incremental insertion, or does not support arbitrary distance metrics. We modify and improve three algorithms to support our scenario of incremental insertion and querying with arbitrary metrics, and evalua…
Adaptive indexing initializes and optimizes indexes incrementally, as a side effect of query processing. The goal is to achieve the benefits of indexes while hiding or minimizing the costs of index creation. However, index-optimizing side effects seem to turn read-only queries into update transactions that might, for example, create lock contention. This paper studies concurrency control in the context of adaptive indexing. We show that the design and implementation of adaptive indexing rigorously separates index structures from index contents; this relaxes the constraints and requirements dur…
Data series similarity search is an important operation and at the core of several analysis tasks and applications related to data series collections. Despite the fact that data series indexes enable fast similarity search, all existing indexes can only answer queries of a single length (fixed at index construction time), which is a severe limitation. In this work, we propose ULISSE, the first data series index structure designed for answering similarity search queries of variable length (within some range). Our contribution is two-fold. First, we introduce a novel representation technique, wh…
Decision systems deal with a large volume of data stored in new databases called data warehouses. Data warehouses are typically modeled by a star schema that conventionally presents a central fact table and a set of dimension tables. The corresponding queries for this type of model are therefore very complex. In order to reduce the cost of executing complex queries, which contain very expensive joins, the solution envisaged would be to guarantee a good physical design of the data warehouses. Binary join indexes are very suitable to reduce the cost of executing these joins. In this work, we pro…
Temporal information plays a crucial role in many database applications, however support for queries on such data is limited. We present an index structure, termed RD-index, to support range-duration queries over interval timestamped relations, which constrain both the range of the tuples' positions on the timeline and their duration. RD-index is a grid structure in the two-dimensional space, representing the position on the timeline and the duration of timestamps, respectively. Instead of using a regular grid, we consider the data distribution for the construction of the grid in order to ensu…
King’s College London（伦敦国王学院）；University of Texas at Dallas（德克萨斯大学达拉斯分校）；North Carolina State University（北卡罗来纳州立大学）；Louisiana State University（路易斯安那州立大学）；The Cyprus Institute（塞浦路斯研究院）
The area query, to find all elements contained in a specified area from a certain set of spatial objects, is a very important spatial query widely required in various fields. A number of approaches have been proposed to implement this query, the best known of which is to obtain a rough candidate set through spatial indexes and then refine the candidates through geometric validations to get the final result. When the shape of the query area is a rectangle, this method has very high efficiency. However, when the query area is irregular, the candidate set is usually much larger than the final res…
Scanning and filtering over multi-dimensional tables are key operations in modern analytical database engines. To optimize the performance of these operations, databases often create clustered indexes over a single dimension or multi-dimensional indexes such as R-trees, or use complex sort orders (e.g., Z-ordering). However, these schemes are often hard to tune and their performance is inconsistent across different datasets and queries. In this paper, we introduce Flood, a multi-dimensional in-memory index that automatically adapts itself to a particular dataset and workload by jointly optimiz…
SPARQL basic graph pattern (BGP) (a.k.a. SQL inner-join) query optimization is a well researched area. However, optimization of OPTIONAL pattern queries (a.k.a. SQL left-outer-joins) poses additional challenges, due to the restrictions on the \textit{reordering} of left-outer-joins. The occurrence of such queries tends to be as high as 50% of the total queries (e.g., DBPedia query logs). In this paper, we present \textit{Left Bit Right} (LBR), a technique for \textit{well-designed} nested BGP and OPTIONAL pattern queries. Through LBR, we propose a novel method to represent such queries using a…
Filtering data based on predicates is one of the most fundamental operations for any modern data warehouse. Techniques to accelerate the execution of filter expressions include clustered indexes, specialized sort orders (e.g., Z-order), multi-dimensional indexes, and, for high selectivity queries, secondary indexes. However, these schemes are hard to tune and their performance is inconsistent. Recent work on learned multi-dimensional indexes has introduced the idea of automatically optimizing an index for a particular dataset and workload. However, the performance of that work suffers in the p…
