arXiv subjects

Hongzhi Wang

Publications and source records attributed to Hongzhi Wang.

119 records · Page 7Linked to original sources

arXiv2018

Diversification on Big Data in Query Processing

Recently, in the area of big data, some popular applications such as web search engines and recommendation systems, face the problem to diversify results during query processing. In this sense, it is both significant and essential to propose methods to deal with big data in order to increase the diversity of the result set. In this paper, we firstly define a set's diversity and an element's ability to improve the set's overall diversity. Based on these definitions, we propose a diversification framework which has good performance in terms of effectiveness and efficiency. Also, this framework has theoretical guarantee on probability of success. Secondly, we design implementation algorithms based on this framework for both numerical and string data. Thirdly, for numerical and string data respectively, we carry out extensive experiments on real data to verify the performance of our proposed framework, and also perform scalability experiments on synthetic data.

cs.DB↗

arXiv2018

Improve3C: Data Cleaning on Consistency and Completeness with Currency

Data quality plays a key role in big data management today. With the explosive growth of data from a variety of sources, the quality of data is faced with multiple problems. Motivated by this, we study the multiple data quality improvement on completeness, consistency and currency in this paper. For the proposed problem, we introduce a 4-step framework, named Improve3C, for detection and quality improvement on incomplete and inconsistent data without timestamps. We compute and achieve a relative currency order among records derived from given currency constraints, according to which inconsistent and incomplete data can be repaired effectively considering the temporal impact. For both effectiveness and efficiency consideration, we carry out inconsistent repair ahead of incomplete repair. Currency-related consistency distance is defined to measure the similarity between dirty records and clean ones more accurately. In addition, currency orders are treated as an important feature in the training process of incompleteness repair. The solution algorithms are introduced in detail with examples. A thorough experiment on one real-life data and a synthetic one verifies that the proposed method can improve the performance of dirty data cleaning with multiple quality problems which are hard to be cleaned by the existing approaches effectively.

cs.DB↗

arXiv2018

MISS: Finding Optimal Sample Sizes for Approximate Analytics

Nowadays, sampling-based Approximate Query Processing (AQP) is widely regarded as a promising way to achieve interactivity in big data analytics. To build such an AQP system, finding the minimal sample size for a query regarding given error constraints in general, called Sample Size Optimization (SSO), is an essential yet unsolved problem. Ideally, the goal of solving the SSO problem is to achieve statistical accuracy, computational efficiency and broad applicability all at the same time. Existing approaches either make idealistic assumptions on the statistical properties of the query, or completely disregard them. This may result in overemphasizing only one of the three goals while neglect the others. To overcome these limitations, we first examine carefully the statistical properties shared by common analytical queries. Then, based on the properties, we propose a linear model describing the relationship between sample sizes and the approximation errors of a query, which is called the error model. Then, we propose a Model-guided Iterative Sample Selection (MISS) framework to solve the SSO problem generally. Afterwards, based on the MISS framework, we propose a concrete algorithm, called $L^2$Miss, to find optimal sample sizes under the $L^2$ norm error metric. Moreover, we extend the $L^2$Miss algorithm to handle other error metrics. Finally, we show theoretically and empirically that the $L^2$Miss algorithm and its extensions achieve satisfactory accuracy and efficiency for a considerably wide range of analytical queries.

cs.DB↗

arXiv2017

Similarity Search Combining Query Relaxation and Diversification

We study the similarity search problem which aims to find the similar query results according to a set of given data and a query string. To balance the result number and result quality, we combine query result diversity with query relaxation. Relaxation guarantees the number of the query results, returning more relevant elements to the query if the results are too few, while the diversity tries to reduce the similarity among the returned results. By making a trade-off of similarity and diversity, we improve the user experience. To achieve this goal, we define a novel goal function combining similarity and diversity. Aiming at this goal, we propose three algorithms. Among them, algorithms genGreedy and genCluster perform relaxation first and select part of the candidates to diversify. The third algorithm CB2S splits the dataset into smaller pieces using the clustering algorithm of k-means and processes queries in several small sets to retrieve more diverse results. The balance of similarity and diversity is determined through setting a threshold, which has a default value and can be adjusted according to users' preference. The performance and efficiency of our system are demonstrated through extensive experiments based on various datasets.

cs.DB↗

arXiv2016

Efficient Web-based Data Imputation with Graph Model

A challenge for data imputation is the lack of knowledge. In this paper, we attempt to address this challenge by involving extra knowledge from web. To achieve high-performance web-based imputation, we use the dependency, i.e.FDs and CFDs, to impute as many as possible values automatically and fill in the other missing values with the minimal access of web, whose cost is relatively large. To make sufficient use of dependencies, We model the dependency set on the data as a graph and perform automatical imputation and keywords generation for web-based imputation based on such graph model. With the generated keywords, we design two algorithms to extract values for imputation from the search results. Extensive experimental results based on real-world data collections show that the proposed approach could impute missing values efficiently and effectively compared to existing approach.

cs.DB↗

arXiv2016

Efficient Entity Resolution on Heterogeneous Records

Entity resolution (ER) is the problem of identifying and merging records that refer to the same real-world entity. In many scenarios, raw records are stored under heterogeneous environment. Specifically, the schemas of records may differ from each other. To leverage such records better, most existing work assume that schema matching and data exchange have been done to convert records under different schemas to those under a predefined schema. However, we observe that schema matching would lose information in some cases, which could be useful or even crucial to ER. To leverage sufficient information from heterogeneous sources, in this paper, we address several challenges of ER on heterogeneous records and show that none of existing similarity metrics or their transformations could be applied to find similar records under heterogeneous settings. Motivated by this, we design the similarity function and propose a novel framework to iteratively find records which refer to the same entity. Regarding efficiency, we build an index to generate candidates and accelerate similarity computation. Evaluations on real-world datasets show the effectiveness and efficiency of our methods.

cs.DB↗

arXiv2016

Data Source Selection for Information Integration in Big Data Era

In Big data era, information integration often requires abundant data extracted from massive data sources. Due to a large number of data sources, data source selection plays a crucial role in information integration, since it is costly and even impossible to access all data sources. Data Source selection should consider both efficiency and effectiveness issues. For efficiency, the approach should achieve high performance and be scalability to fit large data source amount. From effectiveness aspect, data quality and overlapping of sources are to be considered, since data quality varies much from data sources, with significant differences in the accuracy and coverage of the data provided, and the overlapping of sources can even lower the quality of data integrated from selected data sources. In this paper, we study source selection problem in \textit{Big Data Era} and propose methods which can scale to datasets with up to millions of data sources and guarantee the quality of results. Motivated by this, we propose a new object function taking the expected number of true values a source can provide as a criteria to evaluate the contribution of a data source. Based on our proposed index we present a scalable algorithm and two pruning strategies to improve the efficiency without sacrificing precision. Experimental results on both real world and synthetic data sets show that our methods can select sources providing a large proportion of true values efficiently and can scale to massive data sources.

cs.DB↗

arXiv2015

Efficient Influence Maximization in Weighted Independent Cascade Model

Influence maximization(IM) problem is to find a seed set in a social network which achieves the maximal influence spread. This problem plays an important role in viral marketing. Numerous models have been proposed to solve this problem. However, none of them considers the attributes of nodes. Paying all attention to the structure of network causes some trouble applying these models to real-word applications. Motivated by this, we present weighted independent cascade (WIC) model, a novel cascade model which extends the applicability of independent cascade(IC) model by attaching attributes to the nodes. The IM problem in WIC model is to maximize the value of nodes which are influenced. This problem is NP-hard. To solve this problem, we present a basic greedy algorithm and Weight Reset(WR) algorithm. Moreover, we propose Bounded Weight Reset(BWR) algorithm to make further effort to improve the efficiency by bounding the diffusion node influence. We prove that BWR is a fully polynomial-time approximation scheme(FPTAS). Experimentally, we show that with additional node attribute, the solution achieved by WIC model outperforms that of IC model in nearly 90%. The experimental results show that BWR can achieve excellent approximation and faster than greedy algorithm more than three orders of magnitude with little sacrifice of accuracy. Especially, BWR can handle large networks with millions of nodes in several tens of seconds while keeping rather high accuracy. Such result demonstrates that BWR can solve IM problem effectively and efficiently.

cs.SI↗

arXiv2013

Parallelization in Extracting Fresh Information from Online Social Network

Online Social Network (OSN) is one of the most hottest services in the past years. It preserves the life of users and provides great potential for journalists, sociologists and business analysts. Crawling data from social network is a basic step for social network information analysis and processing. As the network becomes huge and information on the network updates faster than web pages, crawling is more difficult because of the limitations of band-width, politeness etiquette and computation power. To extract fresh information from social network efficiently and effectively, this paper presents a novel crawling method and discusses parallelization architecture of social network. To discover the feature of social network, we gather data from real social network, analyze them and build a model to describe the discipline of users' behavior. With the modeled behavior, we propose methods to predict users' behavior. According to the prediction, we schedule our crawler more reasonably and extract more fresh information with parallelization technologies. Experimental results demonstrate that our strategies could obtain information from OSN efficiently and effectively.

cs.SI↗

arXiv2013

Harbinger: An Analyzing and Predicting System for Online Social Network Users' Behavior

Online Social Network (OSN) is one of the hottest innovations in the past years, and the active users are more than a billion. For OSN, users' behavior is one of the important factors to study. This demonstration proposal presents Harbinger, an analyzing and predicting system for OSN users' behavior. In Harbinger, we focus on tweets' timestamps (when users post or share messages), visualize users' post behavior as well as message retweet number and build adjustable models to predict users' behavior. Predictions of users' behavior can be performed with the discovered behavior models and the results can be applied to many applications such as tweet crawler and advertisement.

cs.SI↗

arXiv2012

Efficient Subgraph Matching on Billion Node Graphs

The ability to handle large scale graph data is crucial to an increasing number of applications. Much work has been dedicated to supporting basic graph operations such as subgraph matching, reachability, regular expression matching, etc. In many cases, graph indices are employed to speed up query processing. Typically, most indices require either super-linear indexing time or super-linear indexing space. Unfortunately, for very large graphs, super-linear approaches are almost always infeasible. In this paper, we study the problem of subgraph matching on billion-node graphs. We present a novel algorithm that supports efficient subgraph matching for graphs deployed on a distributed memory store. Instead of relying on super-linear indices, we use efficient graph exploration and massive parallel computing for query processing. Our experimental results demonstrate the feasibility of performing subgraph matching on web-scale graph data.

cs.DB↗