Demand for powerful, high-performance analytics on large Data Bases has been ever growing. Database Management Systems have long shown that descriptive analytics can be supported quite effectively by enriching traditional aggregates with constructs such as Data Cubes and other ROLAPs - thus extending the optimizability and parallelizability of RDBMS. In this paper, we show that these benefits can now be extended to predictive analytics, e.g. clustering, classification and association, by using aggregates in declarative recursive queries. Therefore, we introduce KDDLog, a scalable framework which leverages recursive queries with aggregates and our newly-proposed chain aggregates to enable users to build or customize knowledge discovery models with concise and expressive queries. We further propose specialized compilation techniques for semi-naive fix-point computation in the presence of aggregates, and optimizations for complex recursive queries on distributed data platforms. We provide KDDLib to build knowledge discovery tasks and advanced interfaces to ease users of porting new models. Extensive evaluations on large-scale datasets demonstrate that our approach achieves promising performance gain while offering both increased generality and ease of programming knowledge discovery applications.

Abstract With an escalating arms race to adopt machine learning (ML) in diverse application domains, there is an urgent need to support declarative machine learning over distributed data platforms. Toward this goal, a new framework is needed where users can specify ML tasks in a manner where programming is decoupled from the underlying algorithmic and system concerns. In this paper, we argue that declarative abstractions based on Datalog are natural fits for machine learning and propose a purely declarative ML framework with a Datalog query interface. We show that using aggregates in recursive Datalog programs entails a concise expression of ML applications, while providing a strictly declarative formal semantics. This is achieved by introducing simple conditions under which the semantics of recursive programs is guaranteed to be equivalent to that of aggregate-stratified ones. We further provide specialized compilation and planning techniques for semi-naive fixpoint computation in the presence of aggregates and optimization strategies that are effective on diverse recursive programs and distributed data platforms. To test and demonstrate these research advances, we have developed a powerful and user-friendly system on top of Apache Spark. Extensive evaluations on large-scale datasets illustrate that this approach will achieve promising performance gains while improving both programming flexibility and ease of development and deployment for ML applications.

There is a growing interest in supporting advanced Big Data applications on distributed data processing platforms. Most of these systems support SQL or its dialect as the query interface due to its portability and declarative nature. However, current SQL standard cannot effectively express advanced analytical queries due to its limitation in supporting recursive queries. In this demonstration, we show that this problem can be resolved via a simple SQL extension that delivers greater expressive power by allowing aggregates in recursion. To this end, we propose the Recursive-aggregate-SQL (RASQL) language and its system on top of Apache Spark to express and execute complex queries and declarative algorithms in many applications, such as graph search and machine learning. With a variety of examples, we will (i) show how complicated analytic queries can be expressed with RASQL; (ii) illustrate formal semantics of the powerful new constructs; and (iii) present a user-friendly interface to interact with the RASQL system and monitor the query results.

Thanks to a simple SQL extension, Recursive-aggregate-SQL (RaSQL) can express very powerful queries and declarative algorithms, such as classical graph algorithms and data mining algorithms. A novel compiler implementation allows RaSQL to map declarative queries into one basic fixpoint operator supporting aggregates in recursive queries. A fully optimized implementation of this fixpoint operator leads to superior performance, scalability and portability. Thus, our RaSQL system, which extends Spark SQL with the before-mentioned new constructs and implementation techniques, matches and often surpasses the performance of other systems, including Apache Giraph, GraphX and Myria.

Knowledge bases that summarize web information in RDF triples deliver many benefits, including providing access to encyclopedic knowledge via SPARQL queries and end-user interfaces. As the real world evolves, the knowledge base is updated and the evolution history of entities and their properties becomes of great interest to users. Thus, users need query tools of comparable power and usability to explore such evolution histories or flash-back to the past. An integrated system that supports user-friendly queries and efficient query evaluation on the history of knowledge bases is required. In this paper, we introduce (i) SPARQL T , a temporal extension of SPARQL that expresses powerful structured queries on temporal RDF graphs, (ii) an efficient in-memory query engine that takes advantage of compressed multiversion B+ trees to achieve fast evaluation of SPARQL T queries, and (iii) a query optimizer that improves selectivity estimation of temporal queries and generates efficient join orders using the statistics of temporal RDF graphs. The performance and scalability of our system are validated by extensive experiments on real world datasets, which shows significant performance improvement comparing with other approaches.

There is a growing interest in pattern matching over complex event streams. While many bodies of techniques were proposed to search complex patterns and enhance the expressive power of query language, no previous work focused on supporting a well-defined ranking mechanism over answers using semantic ordering. To satisfy this need, we proposed CEPR, a CEP system capable of ranking matchings and emitting ordered results based on users' intentions via a novel query language. In this demo, we will (i) demonstrate language features, system architecture and functionalities, (ii) show examples of CEPR in various application domains and (iii) present a user-friendly interface to monitor query results and interact with the system in real time.

Approximate Query Processing (AQP) based on sampling is critical for supporting timely and cost-effective analytics over big data. To be applied successfully, AQP must be accompanied by reliable estimates on the quality of sample-produced approximate answers; the two main techniques used in the past for this purpose are (i) closed-form analytic error estimation, and (ii) the bootstrap method. Approach (i) is extremely efficient but lacks generality, whereas (ii) is general but suffers from high computational overhead. Our recently introduced Analytical Bootstrap method combines the strengths of both approaches and provides the basis for our ABS system, which will be demonstrated at the conference. The ABS system models bootstrap by a probabilistic relational model, and extends relational algebra with operations on probabilistic relations to predict the distributions of the AQP results. Thus, ABS entails a very fast computation of bootstrap-based quality measures for a general class of SQL queries, which is several orders of magnitude faster than the standard simulation-based bootstrap. In this demo, we will demonstrate the generality, automaticity, and ease of use of the ABS system, and its superior performance over the traditional approaches described above.