Candidate Tuples Research Articles

Efficient computation of G-Skyline groups on massive data

In many practical applications, G-Skyline query is an important operation to return the best tuple groups, which are not g-dominated by other tuple groups of the same size, from a potentially huge data space. It is found that the existing G-Skyline algorithms cannot deal well with massive data due to high I/O cost and high computation cost. This paper proposes a novel GPR algorithm, which is based on presorting and reuse principle, to compute G-Skyline groups on massive data efficiently. The execution of GPR consists of two phases: acquisition of the candidate tuples and computation of G-Skyline groups. The sublinear-I/O method is proposed in phase 1 to scan the presorted table, which is proved to hold early termination property. This paper devises the basic framework of phase 2 and analyzes its execution cost. The SR strategy is utilized to reuse the subset computation results effectively and reduce the execution cost of phase 2 considerably. The extensive experimental results, conducted on synthetic and real-life data sets, show that GPR outperforms the existing algorithms significantly.

Ranking the big sky: efficient top-k skyline computation on massive data

In many applications, top-k skyline query is an important operation to return k skyline tuples with the highest domination scores in a potentially huge data space. It is analyzed that the existing algorithms cannot process top-k skyline query on massive data efficiently. In this paper, we propose a novel table-scan-based algorithm RSTS to compute top-k skyline results on massive data efficiently. RSTS first builds the presorted table, whose tuples are arranged in the order of round-robin retrieval on sorted column lists. RSTS consists of two phases. In phase 1, the candidate tuples are acquired by the sequential scan on the presorted table. In phase 2, RSTS calculates the domination scores of the candidates and returns query results by another sequential scan. It is proved that RSTS has the characteristic of early termination, along with the theoretical analysis of scan depths. The pruning rule for candidate tuples is devised in this paper. The theoretical pruning effect shows that majority of the skyline results can be discarded directly. The extensive experimental results, conducted on synthetic and real-life data sets, show that RSTS outperforms the existing algorithms significantly.

EnAli: entity alignment across multiple heterogeneous data sources

Entity alignment is the problem of identifying which entities in a data source refer to the same real-world entity in the others. Identifying entities across heterogeneous data sources is paramount to many research fields, such as data cleaning, data integration, information retrieval and machine learning. The aligning process is not only overwhelmingly expensive for large data sources since it involves all tuples from two or more data sources, but also need to handle heterogeneous entity attributes. In this paper, we propose an unsupervised approach, called EnAli, to match entities across two or more heterogeneous data sources. EnAli employs a generative probabilistic model to incorporate the heterogeneous entity attributes via employing exponential family, handle missing values, and also utilize the locality sensitive hashing schema to reduce the candidate tuples and speed up the aligning process. EnAli is highly accurate and efficient even without any ground-truth tuples. We illustrate the performance of EnAli on re-identifying entities from the same data source, as well as aligning entities across three real data sources. Our experimental results manifest that our proposed approach outperforms the comparable baseline.

Evaluating Top-N queries in n-dimensional normed spaces

For the problem of processing top-N queries, the threshold algorithm (TA) is an important method in many scenarios. The model of top-N queries with TA has three characteristics: (1) the ranking function is monotone, (2) the query point is fixed, and (3) TA scans the sorted index lists unidirectionally. In many database applications, however, there are opportunities for evaluating top-N queries with arbitrary query points and generic (not necessarily monotone) ranking functions. In this paper, we propose an approach for evaluating top-N queries in n-dimensional normed spaces. Given a query point Q = (q1,…, qn) in the real vector space ℜn and a generic norm distance d as ranking function, our method employs the norm equivalence theorem in Functional Analysis so that the candidate tuples of top-N query Q with d can be obtained using the Maximum distance d∞. This method projects each qi on its corresponding axis and constructs an interval centered at qi, and then enlarges each interval bidirectionally until the n-dimensional hyperrectangle contains enough candidate tuples so that the top-N tuples are retrieved according to the given norm distance d. Extensive experiments are conducted to measure the performance of our approach for both low-dimensional and high-dimensional data.

Learning Join Queries from User Examples

We investigate the problem of learning join queries from user examples. The user is presented with a set of candidate tuples and is asked to label them as positive or negative examples, depending on whether or not she would like the tuples as part of the join result. The goal is to quickly infer an arbitrary n -ary join predicate across an arbitrary number m of relations while keeping the number of user interactions as minimal as possible. We assume no prior knowledge of the integrity constraints across the involved relations. Inferring the join predicate across multiple relations when the referential constraints are unknown may occur in several applications, such as data integration, reverse engineering of database queries, and schema inference. In such scenarios, the number of tuples involved in the join is typically large. We introduce a set of strategies that let us inspect the search space and aggressively prune what we call uninformative tuples, and we directly present to the user the informative ones—that is, those that allow the user to quickly find the goal query she has in mind. In this article, we focus on the inference of joins with equality predicates and also allow disjunctive join predicates and projection in the queries. We precisely characterize the frontier between tractability and intractability for the following problems of interest in these settings: consistency checking, learnability, and deciding the informativeness of a tuple. Next, we propose several strategies for presenting tuples to the user in a given order that allows minimization of the number of interactions. We show the efficiency of our approach through an experimental study on both benchmark and synthetic datasets.

A Locality Sensitive Hashing Filter for Encrypted Vector Databases

We introduce a filtering methodology based on locality-sensitive hashing LSH and whitening transformation to reduce candidate tuples between which encrypted vector databases EVDBs must compute similarity for query processing. The LSH hashing methodology is efficient for estimating similarities between two vectors. It hashes a vector space using randomly chosen vectors. We can filter vectors that are less similar to the querying vectors by recording which hashed space each vector belongs to. However, if vectors in EVDBs are found locally, then most vectors are in the same hashed space, so the filter will not work. Because we can treat those cases using whitening transformation to distribute the vectors broadly, our proposed filtering methodology will work effectively on any vector space. We also show that our filter reduces the server's query processing cost.

TDEP: efficiently processing top-k dominating query on massive data

In many applications including multicriteria decision making, top-k dominating query is a practically useful tool to return k tuples with the highest domination scores in a potentially huge data space. The existing algorithms, either requiring indexes built on the specific attribute subset, or incurring high I/O cost or memory cost, cannot process top-k dominating query on massive data efficiently. In this paper, a novel algorithm TDEP is proposed to utilize sorted lists built for each attribute with low cost to return top-k dominating result on massive data efficiently. Through analysis, it is found that TDEP can be divided into two phases: growing phase and shrinking phase. In each phase, TDEP retrieves the sorted lists in round-robin fashion and maintains the candidates until the stop condition is satisfied. The theoretical analysis is provided for the execution behavior in two phases. An efficient method is developed to compute the domination scores of tuples with the obtained candidates only. Besides, TDEP adopts early pruning to reduce the number of candidate tuples maintained significantly. The extensive experimental results, conducted on synthetic and real-life data sets, show the significant performance advantage of TDEP over the existing algorithms.

Processing Top-<i>N</i> Queries Based on <i>p</i>-Norm Distances

Top-Nqueries are employed in a wide range of applications to obtain a ranked list of data objects that have the highest aggregate scores over certain attributes. The threshold algorithm (TA) is an important method in many scenarios. However, TA is effective only when the ranking function is monotone and the query point is fixed. In the paper, we propose an approach that alleviates the limitations of TA-like methods for processing top-Nqueries. Based onp-norm distances as ranking functions, our methods utilize the fundamental principle of Functional Analysis so that the candidate tuples of top-Nquery with ap-norm distance can be obtained by the Maximum distance. We conduct extensive experiments to prove the effectiveness and efficiency of our method for both low-dimensional (2, 3 and 4) and high-dimensional (25,50 and 104) data.

Audio Retrieval Based on Chinese Keyword Search in Relational Databases

In this paper, we propose a new method based on Chinese keyword search to select the WAV or MP3 files in audio post-production. First, we listen to each file and label it with Chinese characters, and then classify and store the files in a relational database system. Then, we use the techniques of Chinese keyword search to match query characters and the tuple characters quickly, and to compute similarities between the query and candidate tuples. For the characteristics of Chinese keyword search, we present a ranking strategy and an algorithm to refine the candidate tuples resulting from the first round matching, and finally get top-Nresults of audio files. The experimental results show that our method is efficient and effective.

On contextual ranking queries in databases

In this paper, we identify a novel and interesting type of queries, contextual ranking queries, which return the ranks of query tuples among some context tuples given in the queries. Contextual ranking queries are useful for olap and decision support applications in non-traditional data exploration. They provide a mechanism to quickly identify where tuples stand within the context. In this paper, we extend the sql language to express contextual ranking queries and propose a general partition-based framework for processing them. In this framework, we use a novel method that utilizes bitmap indices built on ranking functions. This method can efficiently identify a small number of candidate tuples, thus achieves lower cost than alternative methods. We analytically investigate the advantages and drawbacks of these methods, according to a preliminary cost model. Experimental results suggest that the algorithm using bitmap indices on ranking functions can be substantially more efficient than other methods.

TJJE: An efficient algorithm for top-k join on massive data

In many applications, top-k join is an important operation to return the k most important join tuples among the potentially huge answer space according to a given ranking function. PBRJ is an algorithm template that generalizes previous top-k join algorithms. In this paper, our analysis shows that PBRJ needs to maintain a large quantity of candidate tuples on massive data. Based on the analysis, this paper proposes a novel top-k join algorithm TJJE which is suitable for handling massive data. By some pre-computed information, TJJE first estimates an upper-bound on scan depth of each joined table. Then it determines the file that contains the join positional index pairs of the top-k join results. A novel algorithm is proposed to retrieve the required join tuples by a single sequential and selective scan on the joined tables. Finally, the top-k join results are obtained by a single scan on the retrieved join tuples. The correctness proof and cost analysis of TJJE are presented in this paper. Extensive experiments show that TJJE maintains up to three orders of magnitude fewer candidate tuples and obtains up to one order of magnitude speedup compared to PBRJ.

Indexing dataspaces with partitions

Dataspaces are recently proposed to manage heterogeneous data, with features like partially unstructured, high dimension and extremely sparse. The inverted index has been previously extended to retrieve dataspaces. In order to achieve more efficient access to dataspaces, in this paper, we first introduce our survey of data features in the real dataspaces. Based on the features observed in our study, several partitioning based index approaches are proposed to accelerate the query processing in dataspaces. Specifically, the vertical partitioning index utilizes the partitions on tokens to merge and compress data. We can both reduce the number of I/O reads and avoid aggregation of data inside a compressed list. The horizontal partitioning index supports pruning partitions of tuples in the top-k query. Thus, we can reduce the computation overhead of irrelevant candidate tuples to the query. Finally, we also propose a hybrid index with both vertical and horizontal partitioning. The extensive experiment results in real data sets demonstrate that our approaches outperform the previous techniques and scale well with the large data size.

Chinese Keyword Search by Indexing in Relational Databases

In this paper, we propose a new method based on index to realize IR-style Chinese keyword search with ranking strategies in relational databases. This method creates an index by using the related information of tuple words and presents a ranking strategy in terms of the nature of Chinese words. For a Chinese keyword query, the index is used to match query search words and the tuple words in index quickly, and to compute similarities between the query and tuples by the ranking strategy, and then the set of identifiers of candidate tuples is generated. Thus, we retrieve top-N results of the query using SQL selection statements and output the ranked answers according to the similarities. The experimental results show that our method is efficient and effective.

SPY-TEC+ : AN INTEGRATED INDEX STRUCTURE FOR k-NEAREST NEIGHBOR QUERIES WITH SEMANTIC PREDICATES IN MULTIMEDIA DATABASE

Recently, advanced multimedia applications, such as geographic information system, and content-based multimedia retrieval system, require the efficient processing of k-nearest neighbor queries over large collection of multimedia objects. These queries usually include the semantic information that is represented by text, as well as the visual information that is represented by a high-dimensional feature vector. Among the available techniques for processing such queries, the incremental nearest neighbor algorithm proposed by Hjaltason and Samet is known as the best choice. However, the R-tree used in their algorithm has no facility capable of partially pruning the candidate tuples that will turn out not to satisfy the semantic predicate. Also, the R-tree does not perform sufficiently well on high-dimensional data even though it provides good results on low or middle-dimensional data. These drawbacks may lead to a poor performance when processing the query. In this paper, we propose an integrated index structure, so-called SPY-TEC+, that provides an efficient method for indexing the visual and semantic feature at the same time using the SPY-TEC that was proposed for indexing high-dimensional data, and the signature file. We also propose an efficient incremental nearest neighbor algorithm for processing k-nearest neighbor queries with visual and semantic predicates on the SPY-TEC+. Finally, we show that the SPY-TEC+ enhances the performance of the SPY-TEC for processing k-nearest neighbor queries with visual and semantic predicates through various experiments.

Supporting early pruning in top- k query processing on massive data

This paper analyzes the execution behavior of “No Random Accesses” (NRA) and determines the depths to which each sorted file is scanned in growing phase and shrinking phase of NRA respectively. The analysis shows that NRA needs to maintain a large quantity of candidate tuples in growing phase on massive data. Based on the analysis, this paper proposes a novel top- k algorithm T op- K with E arly P runing (TKEP) which performs early pruning in growing phase. General rule and mathematical analysis for early pruning are presented in this paper. The theoretical analysis shows that early pruning can prune most of the candidate tuples. Although TKEP is an approximate method to obtain the top- k result, the probability for correctness is extremely high. Extensive experiments show that TKEP has a significant advantage over NRA.