Fast query processing in deductive databases

A special-purpose algorithm, that analyzes the structure of a recursion and exploits its properties in query processing in a deductive database is presented. This method is applied to linear rules, a large and common class of recursion. The structural approach to rule processing (SARP) prototype system that implements the algorithm is described     

Constraint-based query evaluation in deductive databases

Constraints play an important role in the efficient query evaluation in deductive databases. Constraint-based query evaluation in deductive databases is investigated, with emphasis on linear recursions with function symbols. Constraints are grouped into three classes: rule constraints, integrity constraints, and query constraints. Techniques are developed for the maximal use of different kinds of constraints in rule compilation and query evaluation. The study on the roles of different classes of constraints in set-oriented evaluation of linear recursions shows the following: rule constraints should be integrated with their corresponding deduction rules in the compilation of recursions; integrity constraints, including finiteness constraints and monotonicity constraints, should be used in the analysis of finite evaluability and termination for specific queries; and query constraints, which are often useful in search space reduction and termination, should be transformed, when necessary, and should be pushed into the compiled chains as deeply as possible for efficient evaluation. The constraint-based query-processing technique integrates query-independent compilation and chain-based query evaluation methods and demonstrates its great promise in deductive query evaluation     

Perspectives in deductive databases

I discuss my experiences, some of the work that I have done, and related work that influenced me, concerning deductive databases, over the last 30 years. I divide this time period into three roughly equal parts: 1957–1968, 1969–1978, 1979–present. For the first I describe how my interest started in deductive databases in 1957, at a time when the field of databases did not even exist. I describe work in the beginning years, leading to the start of deductive databases about 1968 with the work of Cordell Green and Bertram Raphael. The second period saw a great deal of work in theorem providing as well as the introduction of logic programming. The existence and importance of deductive databases as a formal and viable discipline received its impetus at a workshop held in Toulouse, France, in 1977, which culminated in the book Logic and Data Bases. The relationship of deductive databases and logic programming was recognized at that time. During the third period we have seen formal theories of databases come about as an outgrowth of that work, and the recognition that artificial intelligence and deductive databases are closely related, at least through the so-called expert database systems. I expect that the relationships between techniques from formal logic, databases, logic programming, and artificial intelligence will continue to be explored and the field of deductive databases will become a more prominent area of computer science in coming years.     

Incomplete deductive databases

We investigate the complexity of query processing in databases which have both incompletely specified data and deductive rules. The paper is divided into two parts: in the first we consider databases in which incompletely specified data occurs only in the database intension; in the second we consider databases in which incomplete information is represented only in database extension. We prove that, in general, the query processing problem for databases with incomplete intensions is undecidable. A number of classes of rules for which all conjunctive queries can be processed in polynomial time is then characterized. For databases with incomplete extensions we prove a number of CoNP completeness results. For instance, we demonstrate that processing disjunctions which are restricted to individual columns of database predicates can, in general, be as bad as processing arbitrary disjunctions (i.e. CoNP-complete). This falsifies the conjecture that such limited disjunctions could be computationally beneficial. We also show two simple examples of situations in which query processing is guaranteed to be polynomial. These situations are linked to certain assumptions about database updates.Finally, we provide a summary of the data complexity of queries depending on the type of database extension, intension, query sublanguage and Open World vs Closed World assumption.Research supported by NSF grant DCR 85-04140.More precisely, we can say this only in the presence of the closed world assumption [18].     

Designing deductive databases

We consider the problem of designing schemas for deductive databases. The design problem is to construct a database schema that supports, at minimal expected cost, a given set of database transactions. Our results include a formal definition of both a deductive database schema and a schema transformation. A schema transformation is used in the design process to transform one schema into another, with the goal of reducing the expected database costs. Our design methodology defines the concept of a schema transformation within the context of the clause-based deductive database model. The IDB of the schema that results from the design process includes clauses sufficient for a theorem prover to map queries stated against the original schema into queries against the (more cost effective) resulting schema. This allows users to interact exclusively with the initial schema, while the schema that results from the design process specifies the actual structure of the implemented database. In other words, the initial schema serves as the logical schema for the database, and the result of the design process serves as its physical schema.     

Inductive learning in deductive databases

Most current applications of inductive learning in databases take place in the context of a single extensional relation. The authors place inductive learning in the context of a set of relations defined either extensionally or intentionally in the framework of deductive databases. LINUS, an inductive logic programming system that induces virtual relations from example positive and negative tuples and already defined relations in a deductive database, is presented. Based on the idea of transforming the problem of learning relations to attribute-value form, several attribute-value learning systems are incorporated. As the latter handle noisy data successfully, LINUS is able to learn relations from real-life noisy databases. The use of LINUS for learning virtual relations is illustrated, and a study of its performance on noisy data is presented     

Preference queries in deductive databases

Traditional database query languages such as datalog and SQL allow the user to specify only mandatory requirements on the data to be retrieved from a database. In many applications, it may be natural to express not only mandatory requirements but also preferences on the data to be retrieved. Lacroix and Lavency¹⁰⁾ extended SQL with a notion of preference and showed how the resulting query language could still be translated into the domain relational calculus. We explore the use of preference in databases in the setting of datalog. We introduce the formalism of preference datalog programs (PDPs) as preference logic programs without uninterpreted function symbols for this purpose. PDPs extend datalog not only with constructs to specify which predicate is to be optimized and the criterion for optimization but also with constructs to specify which predicate to be relaxed and the criterion to be used for relaxation. We can show that all of the soft requirements in Reference¹⁰) can be directly encoded in PDP. We first develop anaively-pruned bottom-up evaluation procedure that is sound and complete for computing answers to normal and relaxation queries when the PDPs are stratified, we then show how the evaluation scheme can be extended to the case when the programs are not necessarily stratified, and finally we develop an extension of themagic templates method for datalog¹⁴) that constructs an equivalent but more efficient program for bottom-up evaluation. Kannan Govindarajan, Ph.D.: He obtained his bachelors degree in Computer Science and Engineering from the Indian Institute of Technology, Madras, and he completed his Ph.D. degree in Computer Science from the State University of New York at Buffalo. His dissertation research was on optimization and relaxation techniques for logic languages. His interests lie in the areas of programming languages, databases, and distributed systems. He currently leads the trading community effort in the E-speak Operation in Hewlett Packard Company. Prior to that, he was a member of the Java Products Group in Oracle Corporation. Bharat Jayaraman, Ph.D.: He is a Professor in the Department of Computer Science at the State University of New York at Buffalo. He obtained his bachelors degree in Electronics from the Indian Institute of Technology, Madras (1975), and his Ph.D. from the University of Utah (1981). His research interests are in programming languages and declarative modeling of complex systems. Dr. Jayaraman has published over 50 papers in refereed conferences and journals. He has served on the program committees of several conferences in the area of programming languages, and he is presently on the Editorial Board of the Journal of Functional and Logic Programming. Surya Mantha, Ph.D.: He is a manager in the Communications and Software Services Group of Pittiglio Rabin Todd & McGrath (PRTM), a management consulting firm serving high technology industries. He obtained a bachelors degree in Computer Science and Engineering from the Indian Institute of Technology, Kanpur, an MBA in Finance and Competitive Strategy from the University of Rochester, and a Ph.D. in Computer Science from the University of Utah (1991). His research interests are in the modeling of complex business processes, inter-enterprise application integration, and business strategy. Dr. Mantha has two US patents, and has published over 10 research papers. Prior to joining PRTM, he was a researcher and manager in the Architecture and Document Services Technology Center at Xerox Corporation in Rochester, New York.     

Chain-split evaluation in deductive databases

Many popularly studied recursions in deductive databases can be compiled into one or a set of highly regular chain generating paths, each of which consists of one or a set of connected predicates. Previous studies on chain-based query evaluation in deductive databases take a chain generating path as an inseparable unit in the evaluation. However, some recursions, especially many functional recursions whose compiled chain consists of infinitely evaluable function(s), should be evaluated by chain-split evaluation, which splits a chain generating path into two portions in the evaluation: an immediately evaluable portion and a delayed-evaluation portion. The necessity of chain-split evaluation is examined from the points of view of both efficiency and finite evaluation, and three chain-split evaluation techniques: magic sets, buffered evaluation, and partial evaluation are developed. Our study shows that chain-split evaluation is a primitive recursive query evaluation technique for different kinds of recursions, and it can be implemented efficiently in deductive databases by extensions to the existing recursive query evaluation methods     

Integrity constraint checking in deductive databases using the Prolog not-predicate

In a deductive (or relational) database, integrity constraints are data dependencies which database states are compelled to obey. Different ways of expressing integrity constraints were proposed in several papers, e.g. tuple calculus, closed first-order formula, clause, etc. In this paper, we propose a special form of closed first-order formula, called IC-formula, which uses the Prolog nested not-predicate to express integrity constraints. The IC-formulas are more expressive than other existing ways of expressing integrity constraints. The soundness and completeness of the method for verifying IC-formulas in a deductive database is proved. The full checking of the IC-formulas of a deductive database can be implemented easily by Prolog systems. Methods for doing incremental integrity constraint checking for the operations of inserting, deleting, and modifying a tuple in a relational or deductive database are presented. The concept of a key of a relation is also used to further simplify incremental integrity constraint checking. These incremental integrity constraint checking methods can be implemented easily by Prolog systems.     

Data mining for unemployment rate prediction using search engine query data

Unemployment rate prediction has become critically significant, because it can help government to make decision and design policies. In previous studies, traditional univariate time series models and econometric methods for unemployment rate prediction have attracted much attention from governments, organizations, research institutes, and scholars. Recently, novel methods using search engine query data were proposed to forecast unemployment rate. In this paper, a data mining framework using search engine query data for unemployment rate prediction is presented. Under the framework, a set of data mining tools including neural networks (NNs) and support vector regressions (SVRs) is developed to forecast unemployment trend. In the proposed method, search engine query data related to employment activities is firstly extracted. Secondly, feature selection model is suggested to reduce the dimension of the query data. Thirdly, various NNs and SVRs are employed to model the relationship between unemployment rate data and query data, and genetic algorithm is used to optimize the parameters and refine the features simultaneously. Fourthly, an appropriate data mining method is selected as the selective predictor by using the cross-validation method. Finally, the selective predictor with the best feature subset and proper parameters is used to forecast unemployment trend. The empirical results show that the proposed framework clearly outperforms the traditional forecasting approaches, and support vector regression with radical basis function (RBF) kernel is dominant for the unemployment rate prediction. These findings imply that the data mining framework is efficient for unemployment rate prediction, and it can strengthen government’s quick responses and service capability.     

Transactions and updates in deductive databases

In this paper, we develop a new approach that provides a smooth integration of extensional updates and declarative query languages for deductive databases. The approach is based on a declarative specification of updates in rule bodies. Updates are not executed as soon as evaluated. Instead, they are collected and then applied to the database when the query evaluation is completed. We call this approach nonimmediate update semantics. We provide a top-down and equivalent bottom-up semantics which reflect the corresponding computation models. We also package set of updates into transactions and we provide a formal semantics for transactions. Then, in order to handle complex transactions, we extend the transaction language with control constructors still preserving formal semantics and semantics equivalence     

Inference by generating in deductive databases

A method, APEX, for query evaluation in deductive databases presented in this work is based on discovering of axioms and facts relevant to a given query. The notion of relevancy and migration of facts is derived from an analysis of data flow in the system. APEX is complete, and incorporates efficient query evaluation heuristics. Operation of APEX is illustrated by sample databases involving non-linear recursive axioms and cyclic relations. Main virtues of the method are its generality and adaptivity: it imposes no restrictions on the structure of axioms or the contents of relations, and it employs the knowledge of the actual data acquired at each step of a query evaluation.     

Programming with non-determinism in deductive databases

While non-determinism has long been established as a key concept in logic pro-gramming, its importance in the context of deductive databases was recognized only recently. This paper provides an overview of recent results on this topic with the aim of providing an introduction to the theory and practice of non-determinism in deductive databases. In particular we (i) recall the main results linking non-deterministic constructs in database languages to the theory of data complexity and the expressibility hierarchy of query languages; (ii) provide a reasoned introduction to effective programming with non-deterministic constructs; (iii) compare the usage of non-deterministic constructs in languages such as LDL++ to that of traditional logic programming languages; (iv) discuss the link between the semantics of logic programs with non-deterministic constructs and the stable-model semantics of logic programs with negation.     

Foundations of secure deductive databases

We develop a formal logical foundation for secure deductive databases. This logical foundation is based on an extended logic involving several modal operators. We develop two models of interaction between the user and the database called “yes-no” dialogs, and “yes-no-don't know” dialogs. Both dialog frameworks allow the database to lie to the user. We develop an algorithm for answering queries using yes-no dialogs and prove that secure query processing using yes-no dialogs is NP-complete. Consequently, the degree of computational intractability of query processing with yes-no dialogs is no worse than for ordinary databases. Furthermore, the algorithm is maximally cooperative to user in the sense that lying is resorted to only when absolutely necessary. For Horn databases, we show that secure query processing can be achieved in linear time-hence, this is no more intractable than the situation in ordinary databases. Finally, we identify necessary and sufficient conditions for the database to be able to preserve security. Similar results are also obtained for yes-no-don't know dialogs     

Linear logic for deductive databases

This paper deals with deductive databases in linear logic. The semantics of queries, views, constraints, and (view) updates are defineddeclaratively in linear logic. In constrast to classical logic, we can formalise non-shared view, transition constraints, and (view) updates easily. Various proof search strategies are presented along with an algorithm for query evaluation from a bottom-up direction. An additional advantage is that the associated meaning of a given relation can be defined in terms of the validity of a legal update in a given relation. We also defined formally the update principles and showed the correctness of the update translation algorithms. In this approach, we provide virtual view updates along with real view updates, and view DELETIONs are special cases of view REPLACEMENTs. This permits three transactional view update operations (INSERTION, DELETION, REPLACEMENT) in comparison to only (INSERTION, DELETION) in most existing systems. Dong-Tsan Lee, Ph.D.: He is a computer scientist in the Department of Computer Science at University of Western Australia, Perth, Western Australia, Australia. He received the B.S. and M.S. degrees from the Department of Computer Science at National Chiao-Tung University, Taiwan, in 1983 and 1985, respectively, and earned the Ph.D. degree from the Department of Computer Science at University of Western Australia. His research interests include database and artificial intelligence, linear logic, and real-time software engineering. Chin-Ping Tsang, Ph.D.: He is currently an associate professor in the Department of Computer Science at University of Western Australia, Perth, Western Australia, Australia. He received the Ph.D. degree from the University of Western Australia. He was the head of the Department of Computer Science at the University of Western Australia from 1994 to 1997. His research interests include artificial intelligence, non-classicial logic and neural nets.     

Approaches to deductive object-oriented databases

The paper is concerned with the problem of combining deductive and object-oriented features to produce a deductive object-oriented database system which is comparable to those currently available under the relational view of data modelling not only in its functionality but also in the techniques employed in its construction and use. Under this assumption, the kinds of issues that have to be tackled for a similar research strategy to produce comparable results are highlighted. The authors motivate their terms of comparison, characterize three broad approaches to deductive object-oriented databases and introduce the notion of language convergence to help in the characterization of some shortcomings that have been perceived in them. Three proposals that have come to light in the past three years are looked into in some detail, in so far as they exemplify some of the positions in the space of choices defined. The main contribution of the paper is towards a characterization of the language convergence property of deductive database languages which has a key role in addressing critiques of the deductive and object-oriented database research enterprise. A basic familiarity with notions from deductive databases and from object-oriented databases is assumed.     

DrawCAD: using deductive object‐relational databases in CAD

Computer‐aided design (CAD) involves the use of computers in the various stages of engineering design. CAD has large volumes of data with complex structures that need to be stored and managed effectively and properly. Database systems provide general purpose programs that can be used to access and manipulate large amounts of data stored in the database. They also provide an independence between the program accessing data and the database. It is therefore important to use database systems to store CAD data in the most efficient and effective manner for easy retrieval and better management. Graphical objects can be created, in CAD, by reusing previously created objects. The data of these objects have references to the other objects they contain. Deductive object‐relational databases not only provide direct support for the effective storage and efficient access to large amounts of data with complex structures on disk, but also perform the inferences and computations to obtain the complete data of graphical objects that reuse other objects. They should be able to play a major role in CAD systems. This is the idea behind the development of the DrawCAD system. DrawCAD is a CAD system built on top of the Relationlog object‐relational deductive database system. It facilitates the creation of graphical objects by reusing previously created objects. The DrawCAD system illustrates how CAD systems can be developed, using database systems to store and manage data and also perform the inferences and computations that are normally performed by the application program. Copyright © 2003 John Wiley & Sons, Ltd.     

Partial evaluation of queries in deductive databases

This paper presents some applications of partial evaluation method to a query optimization in deductive database. A Horn clause transformation is used for the partial evaluation of a query in an intensional database, and its application to multiple query processing is discussed. Three strategies are presented for the compatible case, ordered case and crossed case. In each case, partial evaluation is used to preprocess the intensional database in order to obtain subqueries which direct access to an extensional database.