Query Processing Strategies Research Articles

FACET: Robust Counterfactual Explanation Analytics

Machine learning systems are deployed in domains such as hiring and healthcare, where undesired classifications can have serious ramifications for the user. Thus, there is a rising demand for explainable AI systems which provide actionable steps for lay users to obtain their desired outcome. To meet this need, we propose FACET, the first explanation analytics system which supports a user in interactively refining counterfactual explanations for decisions made by tree ensembles. As FACET's foundation, we design a novel type of counterfactual explanation called the counterfactual region. Unlike traditional counterfactuals, FACET's regions concisely describe portions of the feature space where the desired outcome is guaranteed, regardless of variations in exact feature values. This property, which we coin explanation robustness, is critical for the practical application of counterfactuals. We develop a rich set of novel explanation analytics queries which empower users to identify personalized counterfactual regions that account for their real-world circumstances. To process these queries, we develop a compact high-dimensional counterfactual region index along with index-aware query processing strategies for near real-time explanation analytics. We evaluate FACET against state-of-the-art explanation techniques on eight public benchmark datasets and demonstrate that FACET generates actionable explanations of similar quality in an order of magnitude less time while providing critical robustness guarantees. Finally, we conduct a preliminary user study which suggests that FACET's regions lead to higher user understanding than traditional counterfactuals.

Shedding strategies for optimizing join processing in spatial data streams

A core component of any data stream query processing system is a shedding module, which must make decisions on which data to select and discard in order to make room for new incoming data. Although strategies for shedding have been studied in detail for systems that handle alphanumeric data, the subject has received very little attention in the area of spatial data stream query processing. This paper proposes several strategies for object shedding for spatial data stream query processing. These strategies employ spatial data properties, object properties and non-spatial properties in order to decide which objects to discard when space is needed. An evaluation and comparison versus a spatial stream query processing strategy which utilizes FIFO shedding shows that the shedding strategies which employ spatial data properties make the best choices which result in the highest accuracies overall and high accuracies in many cases.

Unbounded Spatial Data Stream Query Processing using Spatial Semijoins

In this paper, the problem of query processing in spatial data streams is explored, with a focus on the spatial join operation. Although the spatial join has been utilized in many proposed centralized and distributed query processing strategies, for its application to spatial data streams the spatial join operation has received very little attention. One identified limitation with existing strategies is that a bounded region of space (i.e., spatial extent) from which the spatial objects are generated needs to be known in advance. However, this information may not be available. Therefore, two strategies for spatial data stream join processing are proposed where the spatial extent of the spatial object stream is not required to be known in advance. Both strategies estimate the common region that is shared by two or more spatial data streams in order to process the spatial join. An evaluation of both strategies includes a comparison with a recently proposed approach in which the spatial extent of the data set is known. Experimental results show that one of the strategies performs very well at estimating the common region of space using only incoming objects on the spatial data streams. Other limitations of this work are also identified.

GoFast: Graph-based optimization for efficient and scalable query evaluation

The popularity of the Resource Description Framework (RDF) and SPARQL has thrust the development of high-performance systems to manage data represented with this model. Former approaches adapted the well-established relational model applying its storage, query processing, and optimization strategies. However, the borrowed techniques from the relational model are not universally applicable in the RDF context. First, the schema-free nature of RDF induces intensive joins overheads. Also, optimization strategies trying to find the optimal join order rely on error-prone statistics unable to capture all the correlations among triples. Graph-based approaches keep the graph structure of RDF representing the data directly as a graph. Their execution model leans on graph exploration operators to find subgraph matches to a query. Even if they have shown to outperform relational-based systems in complex queries, they are barely scalable and optimization techniques are completely system dependent. Recently, some systems such as RDF_QDAG have shown that by combining graph exploration and triples clustering one can achieve a good compromise between performance and scalability. In this paper, we propose optimization strategies for this kind of RDF management systems. First, we define novel statistics collected for clusters of triples to better capture the dependencies found in the original graph. Second, we redefine an execution plan based on these logical structures which allows to represent the RDF graph exploration process. Third, we introduce an algorithm for selecting the optimal execution plan based on a customized cost model. Finally, we propose a new approach to refine the chosen plan by pruning invalid clusters that do not participate in the construction of the final query results. All our proposals are validated experimentally using well-known RDF benchmarks.

AggChecker

We demonstrate AggChecker, a novel tool for verifying textual summaries of relational data sets. The system automatically verifies natural language claims about numerical aggregates against the underlying raw data. The system incorporates a combination of natural language processing, information retrieval, machine learning, and efficient query processing strategies. Each claim is translated into a semantically equivalent SQL query and evaluated against the database. Our primary goal is analogous to that of a spell-checker: to identify erroneous claims and provide guidance in correcting them. In this demonstration, we show that our system enables users to verify text summaries much more efficiently than a standard SQL interface.

Massively Distributed Time Series Indexing and Querying

Indexing is crucial for many data mining tasks that rely on efficient and effective similarity query processing. Consequently, indexing large volumes of time series, along with high performance similarity query processing, have became topics of high interest. For many applications across diverse domains though, the amount of data to be processed might be intractable for a single machine, making existing centralized indexing solutions inefficient. We propose a parallel indexing solution that gracefully scales to billions of time series, and a parallel query processing strategy that, given a batch of queries, efficiently exploits the index. Our experiments, on both synthetic and real world data, illustrate that our index creation algorithm works on four billion time series in less than five hours, while the state of the art centralized algorithms do not scale and have their limit on 1 billion time series, where they need more than five days. Also, our distributed querying algorithm is able to efficiently process millions of queries over collections of billions of time series, thanks to an effective load balancing mechanism.

A method for fuzzy quantified querying over fuzzy Resource Description Framework graph

Vagueness (or imprecision) naturally arises in real-world Resource Description Framework (RDF) data. The way we query RDF data is a crucial subject because of the vagueness and the wide connectivity of such data. Fuzzy quantified queries have been studied over several types of data and allow to sum up large volumes of data in a very intuitive manner. However, there are a few works that have been led on RDF graph database. In this study, we dealt with a specific type of fuzzy quantified queries in the context of a (fuzzy) RDF graph database. We first show how these queries can be expressed and interpreted in a quantified graph pattern, which is an extension of graph patterns by supporting linguistic quantifier on edges. A query processing strategy based on subgraph matching queries is also proposed. Then, we develop an algorithm for evaluating quantified RDF graph patterns, that is, enumerating all RDF isomorphism from the given RDF graph patterns into the data graph. The algorithm is based on a backtracking strategy, which incrementally finds partial solutions by adding joinable candidate vertices or abandoning them when it determines they cannot be completed. Finally, we perform some experiments to study its performances. The results of these experiments show that the method of dealing with fuzzy quantification in a query is feasible.

Continuous Region Query Processing in Clustered Point Sets

There exists an increasing usage rate of location-based information from mobile devices, which requires new query processing strategies. One such strategy is a continuous region query in which a moving user continuously sends queries to a central server to obtain data or information. In this paper, we introduce two strategies to process a spatial moving query over clustered data sets. Both strategies use a safe region approach on the client in order to minimize the number of queries that are sent to the server. We explore the use of a two-dimensional indexing strategy, as well as the use of Expectation Maximization (EM) and k-means clustering. Our experiments show that both strategies outperform a Baseline strategy where all queries are sent to the server, with respect to data transmission, running time and workload costs.

Trade-offs Computing Minimum Hub Cover toward Optimized Labeled Graph Query Processing

As techniques for graph query processing mature, the need for optimization is increasingly becoming an imperative. Query processing aids such as indices are one of the key ingredients toward efficient query processing strategies via cost-based optimization. Due to the apparent absence of a common representation model, it is difficult to make a focused effort toward developing access structures, metrics to evaluate query costs, and choose alternatives. In this context, recent interests in covering-based graph matching appears to be a promising direction of research. In this paper, our goal is to formally introduce a new graph representation model, called Minimum Hub Cover, and demonstrate that this representation offers interesting strategic advantages, facilitates construction of candidate graphs from graph fragments, and helps leverage indices in novel ways for query optimization. However, similar to other covering problems, minimum hub cover is NP-hard, and thus is a natural candidate for optimization. We claim that computing the minimum hub cover leads to substantial cost reduction for graph query processing. We present a computational characterization of minimum hub cover based on integer programming to substantiate our claim and investigate its computational cost on various graph types.

SkinnerDB

Robust query optimization becomes illusory in the presence of correlated predicates or user-defined functions. Occasionally, the query optimizer will choose join orders whose execution time is by many orders of magnitude higher than necessary. We present SkinnerDB, a novel database management system that is designed from the ground up for reliable optimization and robust performance. SkinnerDB implements several adaptive query processing strategies based on reinforcement learning. We divide the execution of a query into small time periods in which different join orders are executed. Thereby, we converge to optimal join orders with regret bounds, meaning that the expected difference between actual execution time and time for an optimal join order is bounded. To the best of our knowledge, our execution strategies are the first to provide comparable formal guarantees. SkinnerDB can be used as a layer on top of any existing database management system. We use optimizer hints to force existing systems to try out different join orders, carefully restricting execution time per join order and data batch via timeouts. We choose timeouts according to an iterative scheme that balances execution time over different timeouts to guarantee bounded regret. Alternatively, SkinnerDB can be used as a standalone, featuring an execution engine that is tailored to the requirements of join order learning. In particular, we use a specialized multi-way join algorithm and a concise tuple representation to facilitate fast switches between join orders. In our demonstration, we let participants experiment with different query types and databases. We visualize the learning process and compare against baselines.

Energy Efficiency in Large Scale Information Retrieval Systems

Web search engines are large scale information retrieval systems, which provide easy access to information on the Web. High performance query processing is fundamental for the success of such systems. In fact, web search engines can receive billions of queries per day. Additionally, the issuing users are often impatient and expect sub-second response times to their queries (e.g., 500 ms). For such reasons, search companies adopt distributed query processing strategies to cope with huge volumes of incoming queries and to provide sub-second response times. Web search engines perform distributed query processing on computer clusters composed by thousands of computers and hosted in large data centers. While data center facilities enable large-scale online services, they also raise economical and environmental concerns. Therefore, an important problem to address is how to reduce the energy expenditure of data centers. Moreover, another problem to tackle is how to reduce carbon dioxide emissions and the negative impact of the data centers on the environment. A large part of the energy consumption of a data center could be accounted to inefficiencies in its cooling and power supply systems. However, search companies already adopt state-of-the art techniques to reduce the energy wastage of such systems, leaving little room for more improvements in those areas. Therefore, new approaches are necessary to mitigate the environmental impact and the energy expenditure of web search engines. One option is to reduce the energy consumption of computing resources to mitigate the energy expenditure and carbon footprint of a search company. In particular, reducing the energy consumption of CPUs represents an attractive venue for web search engines. Currently, CPU cores frequencies are typically managed by operating system components, called frequency governors. We propose to delegate the CPU power management from the OS frequency governors to the query processing application [2]. Such search engine-specific governors can reduce up to 24% a server power consumption, with only limited (but uncontrollable) drawbacks in the quality of search results with respect to a system running at maximum CPU frequency. Since users can hardly notice response times that are faster than their expectations we advise that web search engine should not process queries faster than user expectations and, consequently, we propose the Predictive Energy Saving Online Scheduling (PESOS) algorithm, to select the most appropriate CPU frequency to process a query by its deadline, on a per-core basis [3]. PESOS can reduce the CPU energy consumption of a query processing server from 24% up to 48% when compared to a high performance system running at maximum CPU core frequency. To reduce the carbon footprint of web search engines, another option consists in using green energy to partially power their data centers. Stemming from these observations, we propose a new query forwarding algorithm that exploits both the green energy sources available at different data centers and the differences in market energy prices [1]. The proposed solution maintains a high query throughput, while reducing by up to 25% the energy operational costs of multi-center search engines.

Augmented keyword search on spatial entity databases

In this paper, we propose a new type of query that augments the spatial keyword search with an additional boolean expression constraint. The query is issued against a corpus of structured or semi-structured spatial entities and is very useful in applications like mobile search and targeted location-aware advertising. We devise three types of indexing and filtering strategies. First, we utilize the hybrid $$\hbox {IR}^2$$ -tree and propose a novel hashing scheme for efficient pruning. Second, we propose an inverted index-based solution, named BE-Inv, that is more cache concious and exhibits great pruning power for boolean expression matching. Our third method, named SKB-Inv, adopts a novel two-level partitioning scheme to organize the spatial entities into inverted lists and effectively facilitate the pruning in the spatial, textual, and boolean expression dimensions. In addition, we propose an adaptive query processing strategy that takes into account the selectivity of query keywords and predicates for early termination. We conduct our experiments using two real datasets with 3.5 million Foursquare venues and 50 million Twitter geo-profiles. The results show that the methods based on inverted index are superior to the hybrid $$\hbox {IR}^2$$ -tree; and SKB-Inv achieves the best performance.

VRSense: Validity region sensitive query processing strategies for static and mobile point-of-interests in MANETs

Querying any point-of-interest (POI) in anywhere is a major part of location-based services (LBS) and has been applied to diverse wireless and/or mobile networks for realizing seamless services and mobile and ubiquitous computing. In particular, designing an efficient query processing scheme is admittedly challenging in mobile ad hoc networks (MANETs) because of the lack of centralized coordination, limited computing and communication capabilities, and time-varying network topologies. Unlike traditional stationary POIs, it also becomes challenging to consider mobile POIs that can invalidate prior query result. To address these challenges, we propose a set of query processing strategies based on a validity region to efficiently update the freshness of the queried POI and reduce the query traffic in MANETs. We first present and analyze time- and location-sensitive query types in the presence of static and mobile POIs and identify their corresponding query processing operations and implications. A time-sensitive query targets a POI containing a time-varying information while a location-sensitive query retrieves a location information. In this paper, we focus on location-sensitive query for both static and mobile POIs. Unlike a static POI, which is stationary and never changes its location, a mobile POI refers to a moving object and its location information is time varying. Then we propose basic rectangle and convex hull based validity regions and their corresponding query processing operations, and extend them by combining both techniques and considering an opportunistic overhearing. We also propose two more techniques in forming validity region for mobile POIs and their corresponding query processing operations to flexibly approximate the validity region. We conduct extensive simulation experiments using the OMNeT++ for performance evaluation and analysis, in which an infrastructure-based query processing approach is modified to work in MANETs for performance comparison. The simulation results indicate that the validity region based query processing strategies can reduce the number of queries and increase the time staying in the validity region.

Waves: a fast multi-tier top-k query processing algorithm

In this paper, we present Waves, a novel document-at-a-time algorithm for fast computing of top-k query results in search systems. The Waves algorithm uses multi-tier indexes for processing queries. It performs successive tentative evaluations of results which we call waves. Each wave traverses the index, starting from a specific tier level i. Each wave i may insert only those documents that occur in that tier level into the answer. After processing a wave, the algorithm checks whether the answer achieved might be changed by successive waves or not. A new wave is started only if it has a chance of changing the top-k scores. We show through experiments that such lazy query processing strategy results in smaller query processing times when compared to previous approaches proposed in the literature. We present experiments to compare Waves’ performance to the state-of-the-art document-at-a-time query processing methods that preserve top-k results and show scenarios where the method can be a good alternative algorithm for computing top-k results.

Distributed Query Plan Generation using Cuckoo Search Algorithm

Query processing in distributed databases involves data transmission amongst sites capable of providing answers to a distributed query. For this, a distributed query processing strategy, which generates efficient query processing plans for a given distributed query, needs to be devised. Since in distributed databases, the data is fragmented and replicated at multiple sites, the number of query plans increases exponentially with increase in the number of sites capable of providing answers to a distributed query. As a result, generating efficient query processing plans, from amongst all possible query plans, becomes a complex problem. This distributed query plan generation (DQPG) problem has been addressed using the Cuckoo Search Algorithm (CSA) in this paper. Accordingly, a CSA based DQPG algorithm (DQPGCSA) that aims to generate Top-K query plans having minimum cost of processing a distributed query has been proposed. Experimental based comparison of DQPGCSA with the existing GA based DQPG algorithm shows that the former is able to generate Top-K query plans that have a comparatively lower query processing cost. This, in turn, reduces the query response time resulting in efficient decision making.

Distributed Query Plan Generation Using Firefly Algorithm

A large number of queries are posed daily against the distributed databases spread across the globe. Query processing strategies are used to generate efficient query plans for these queries. The number of such query plans increases exponentially with the increase in the number of involved sites and relations accessed by the query. Further, this complexity increases if the data is fragmented and replicated across multiple sites. This problem, referred to as the distributed query plan generation (DQPG) problem, is a combinatorial optimization problem. An attempt has been made in this paper to solve this DQPG problem using the Firefly Algorithm (FA), which is inspired by the flashing behaviour of fireflies in nature. The proposed FA based DQPG algorithm (DQPGFA), aims to generate distributed query plans incurring minimum Query Proximity Cost (QPC) value. The experimental results show that DQPGFA, in comparison to the GA based DQPG algorithm (DQPGGA), was able to select Top-K query plans that had a comparatively lesser average QPC value. Such generated query plans would, most likely, lead to an improvement in the query response time and thereby would result in effective and efficient decision making.

CEPSim: Modelling and simulation of Complex Event Processing systems in cloud environments

The emergence of Big Data has had profound impacts on how data are stored and processed. As technologies created to process continuous streams of data with low latency, Complex Event Processing (CEP) and Stream Processing (SP) have often been related to the Big Data velocity dimension and used in this context. Many modern CEP and SP systems leverage cloud environments to provide the low latency and scalability required by Big Data applications, yet validating these systems at the required scale is a research problem per se. Cloud computing simulators have been used as a tool to facilitate reproducible and repeatable experiments in clouds. Nevertheless, existing simulators are mostly based on simple application and simulation models that are not appropriate for CEP or for SP. This article presents CEPSim, a simulator for CEP and SP systems in cloud environments. CEPSim proposes a query model based on Directed Acyclic Graphs (DAGs) and introduces a simulation algorithm based on a novel abstraction called event sets. CEPSim is highly customizable and can be used to analyse the performance and scalability of user-defined queries and to evaluate the effects of various query processing strategies. Experimental results show that CEPSim can simulate existing systems in large Big Data scenarios with accuracy and precision.

Design and Implementation of Spatial Operators and Energy-Efficient Query Processing Strategy in Wireless Sensor Network Database System

Database applications in wireless sensor networks very often demand data collection from sensor nodes of specific target regions. Design and development of spatial query expressions and energy-efficient query processing strategy are important issues for sensor network database systems. The existing sensor network database systems lack the needed sophistication for the space calculation of the target sensor nodes; hence, unnecessary query/data transmissions are required between the sensor nodes and the server. This paper describes our spatial operations and energy-efficient query processing methods that are designed and implemented in our sensor network database system called [Formula: see text]. With a set of spatial operators based on geometric parameters, such as Envelope, NearBy, Distance, Direction, and set theoretic operators, [Formula: see text] allows sensor network applications to easily specify the target space of interest. Our energy-efficient query processing strategy implements an in-network query management based on the lowest common ancestor (LCA) algorithm, so that the query processing cost for calculating the target spaces is greatly reduced by avoiding the need of heavy query/data transmissions between the base-station and target nodes. Performance evaluation shows that our proposed design and implementation of spatial query expressions and processing strategy achieve improved energy efficiency for database operations in the wireless sensor network.

Distributed query plan generation using BCO

Distributed query processing entails accessing data from multiple sites. In addition to the usual disk IO and CPU costs, the cost due to transmission of data between different sites, referred to as the site-to-site communication cost, also exists. This cost, being the major cost, needs to be reduced in order to improve the response time for distributed queries. One way to reduce this communication cost is by devising a distributed query processing strategy that involves fewer number of sites for answering the distributed queries. In this paper, a distributed query plan generation (DQPG) algorithm based on bee colony optimisation (BCO), which generates distributed query plans that involves less number of sites and have higher relation concentration in the participating sites, is presented. Additionally, the experimental comparison of the BCO-based DQPG algorithm with the GA-based DQPG algorithm exhibits that the former is able to generate comparatively better quality top-K query plans for a given distribut...

Distributed Query Plan Generation using Ant Colony Optimization

Query processing is a critical performance evaluation parameter and has received a considerable amount of attention especially in the context of distributed database systems. The aim of distributed query processing is to effectively and efficiently process the query. This entails laying down an optimal distributed query processing strategy that generates efficient query plans Since in distributed database systems, the data is distributed and replicated at multiple sites, the number of query plans increases exponentially with increase in the number of relations accessed by the query along with increase in the number of sites containing these relations. Thus, from amongst these query plans, there is a need to generate optimal query plans involving lesser number of sites which, in turn, would entail lower site-to-site communication cost leading to faster query response times. In this paper, an attempt has been made to generate such query plans for a distributed query using Ant Colony Optimization (ACO). This ACO based distributed query plan generation (DQPG) algorithm, when compared with the GA based DQPG algorithm, is able to generate comparatively better quality Top-K query plans for a given distributed query.