Computer Science

Most of today's persistent key-value stores are based either on a write-optimized Log-Structured Merge tree (LSM) or a read-optimized B+-tree, both of which assume that there is not enough memory to cache the entire data set. As RAM is becoming cheaper and more abundant, it is time to revisit the design of persistent key-value storage systems. This paper introduces a new design called "lazy-trie" to index the persistent storage, a variant of the hash-trie data structure, optimized to cache entirely in memory. A lazy-trie achieves near-optimal height and has practical storage overhead, but does not support range queries. We implemented CedrusDB, a lazy-trie-based persistent key-value store. The implementation uses memory-mapping. The lazy-trie organization in virtual memory allows CedrusDB to better leverage concurrent processing than other organizations. CedrusDB achieves comparable or superior performance for both popular LSM- and B+-tree-based key-value stores in mixed workloads.

Modern database systems are growing increasingly distributed and struggle to reduce query completion time with a large volume of data. In this paper, we leverage programmable switches in the network to partially offload query computation to the switch. While switches provide high performance, they have resource and programming constraints that make implementing diverse queries difficult. To fit in these constraints, we introduce the concept of data \emph{pruning} -- filtering out entries that are guaranteed not to affect output. The database system then runs the same query but on the pruned data, which significantly reduces processing time. We propose pruning algorithms for a variety of queries. We implement our system, Cheetah, on a Barefoot Tofino switch and Spark. Our evaluation on multiple workloads shows 40−200% improvement in the query completion time compared to Spark.

Data cleaning is a time-consuming process that depends on the data analysis that users perform. Existing solutions treat data cleaning as a separate offline process that takes place before analysis begins. Applying data cleaning before analysis assumes a priori knowledge of the inconsistencies and the query workload, thereby requiring effort on understanding and cleaning the data that is unnecessary for the analysis. We propose an approach that performs probabilistic repair of denial constraint violations on-demand, driven by the exploratory analysis that users perform. We introduce Daisy, a system that seamlessly integrates data cleaning into the analysis by relaxing query results. Daisy executes analytical query-workloads over dirty data by weaving cleaning operators into the query plan. Our evaluation shows that Daisy adapts to the workload and outperforms traditional offline cleaning on both synthetic and real-world workloads.

Big Data is used by data miner for analysis purpose which may contain sensitive information. During the procedures it raises certain privacy challenges for researchers. The existing privacy preserving methods use different algorithms that results into limitation of data reconstruction while securing the sensitive data. This paper presents a clustering based privacy preservation probabilistic model of big data to secure sensitive information..model to attain minimum perturbation and maximum privacy. In our model, sensitive information is secured after identifying the sensitive data from data clusters to modify or generalize it.The resulting dataset is analysed to calculate the accuracy level of our model in terms of hidden data, lossed data as result of reconstruction. Extensive experiements are carried out in order to demonstrate the results of our proposed model. Clustering based Privacy preservation of individual data in big data with minimum perturbation and successful reconstruction highlights the significance of our model in addition to the use of standard performance evaluation measures.

Many modern applications produce massive streams of data series and maintain them in indexes to be able to explore them through nearest neighbor search. Existing data series indexes, however, are expensive to operate as they issue many random I/Os to storage. To address this problem, we recently proposed Coconut, a new infrastructure that organizes data series based on a new sortable format. In this way, Coconut is able to leverage state-of-the-art indexing techniques that rely on sorting for the first time to build, maintain and query data series indexes using fast sequential I/Os. In this demonstration, we present Coconut Palm, a new exploration tool that allows to interactively combine different indexing techniques from within the Coconut infrastructure and to thereby seamlessly explore data series from across various scientific domains. We highlight the rich indexing design choices that Coconut opens up, and we present a new recommender tool that allows users to intelligently navigate them for both static and streaming data exploration scenarios.

Many modern applications produce massive amounts of data series that need to be analyzed, requiring efficient similarity search operations. However, the state-of-the-art data series indexes that are used for this purpose do not scale well for massive datasets in terms of performance, or storage costs. We pinpoint the problem to the fact that existing summarizations of data series used for indexing cannot be sorted while keeping similar data series close to each other in the sorted order. This leads to two design problems. First, traditional bulk-loading algorithms based on sorting cannot be used. Instead, index construction takes place through slow top-down insertions, which create a non-contiguous index that results in many random I/Os. Second, data series cannot be sorted and split across nodes evenly based on their median value; thus, most leaf nodes are in practice nearly empty. This further slows down query speed and amplifies storage costs. To address these problems, we present Coconut. The first innovation in Coconut is an inverted, sortable data series summarization that organizes data series based on a z-order curve, keeping similar series close to each other in the sorted order. As a result, Coconut is able to use bulk-loading techniques that rely on sorting to quickly build a contiguous index using large sequential disk I/Os. We then explore prefix-based and median-based splitting policies for bottom-up bulk-loading, showing that median-based splitting outperforms the state of the art, ensuring that all nodes are densely populated. Overall, we show analytically and empirically that Coconut dominates the state-of-the-art data series indexes in terms of construction speed, query speed, and storage costs.

Many modern applications produce massive streams of data series that need to be analyzed, requiring efficient similarity search operations. However, the state-of-the-art data series indexes that are used for this purpose do not scale well for massive datasets in terms of performance, or storage costs. We pinpoint the problem to the fact that existing summarizations of data series used for indexing cannot be sorted while keeping similar data series close to each other in the sorted order. To address this problem, we present Coconut, the first data series index based on sortable summarizations and the first efficient solution for indexing and querying streaming series. The first innovation in Coconut is an inverted, sortable data series summarization that organizes data series based on a z-order curve, keeping similar series close to each other in the sorted order. As a result, Coconut is able to use bulk loading and updating techniques that rely on sorting to quickly build and maintain a contiguous index using large sequential disk I/Os. We then explore prefix-based and median-based splitting policies for bottom-up bulk loading, showing that median-based splitting outperforms the state of the art, ensuring that all nodes are densely populated. Finally, we explore the impact of sortable summarizations on variable-sized window queries, showing that they can be supported in the presence of updates through efficient merging of temporal partitions. Overall, we show analytically and empirically that Coconut dominates the state-of-the-art data series indexes in terms of construction speed, query speed, and storage costs.

Knowledge graphs have become a popular formalism for representing entities and their properties using a graph data model, e.g., the Resource Description Framework (RDF). An RDF graph comprises entities of the same type connected to objects or other entities using labeled edges annotated with properties. RDF graphs usually contain entities that share the same objects in a certain group of properties, i.e., they match star patterns composed of these properties and objects. In case the number of these entities or properties in these star patterns is large, the size of the RDF graph and query processing are negatively impacted; we refer these star patterns as frequent star patterns. We address the problem of identifying frequent star patterns in RDF graphs and devise the concept of factorized RDF graphs, which denote compact representations of RDF graphs where the number of frequent star patterns is minimized. We also develop computational methods to identify frequent star patterns and generate a factorized RDF graph, where compact RDF molecules replace frequent star patterns. A compact RDF molecule of a frequent star pattern denotes an RDF subgraph that instantiates the corresponding star pattern. Instead of having all the entities matching the original frequent star pattern, a surrogate entity is added and related to the properties of the frequent star pattern; it is linked to the entities that originally match the frequent star pattern. We evaluate the performance of our factorization techniques on several RDF graph benchmarks and compare with a baseline built on top of gSpan, a state-of-the-art algorithm to detect frequent patterns. The outcomes evidence the efficiency of proposed approach and show that our techniques are able to reduce execution time of the baseline approach in at least three orders of magnitude reducing the RDF graph size by up to 66.56%.

Many modern navigation systems and map-based services do not only provide the fastest route from a source location s to a target location t but also provide a few alternative routes to the users as more options to choose from. Consequently, computing alternative paths has received significant research attention. However, it is unclear which of the existing approaches generates alternative routes of better quality because the quality of these alternatives is mostly subjective. Motivated by this, in this paper, we present a user study conducted on the road networks of Melbourne, Dhaka and Copenhagen that compares the quality (as perceived by the users) of the alternative routes generated by four of the most popular existing approaches including the routes provided by Google Maps. We also present a web-based demo system that can be accessed using any internet-enabled device and allows users to see the alternative routes generated by the four approaches for any pair of selected source and target. We report the average ratings received by the four approaches and our statistical analysis shows that there is no credible evidence that the four approaches receive different ratings on average. We also discuss the limitations of this user study and recommend the readers to interpret these results with caution because certain factors may have affected the participants' ratings.

As the need for machine learning (ML) increases rapidly across all industry sectors, there is a significant interest among commercial database providers to support "Query 2.0", which integrates model inference into SQL queries. Debugging Query 2.0 is very challenging since an unexpected query result may be caused by the bugs in training data (e.g., wrong labels, corrupted features). In response, we propose Rain, a complaint-driven training data debugging system. Rain allows users to specify complaints over the query's intermediate or final output, and aims to return a minimum set of training examples so that if they were removed, the complaints would be resolved. To the best of our knowledge, we are the first to study this problem. A naive solution requires retraining an exponential number of ML models. We propose two novel heuristic approaches based on influence functions which both require linear retraining steps. We provide an in-depth analytical and empirical analysis of the two approaches and conduct extensive experiments to evaluate their effectiveness using four real-world datasets. Results show that Rain achieves the highest recall@k among all the baselines while still returns results interactively.