Sergey Paramonov

An Exercise in Declarative Modeling for Relational Query Mining

Motivated by the declarative modeling paradigm for data mining, we report on our experience in modeling and solving relational query and graph mining problems with the IDP system, a variation on the answer set programming paradigm. Using IDP or other ASP-languages for modeling appears to be natural given that they provide rich logical languages for modeling and solving many search problems and that relational query mining (and ILP) is also based on logic. Nevertheless, our results indicate that second order extensions to these languages are necessary for expressing the model as well as for efficient solving, especially for what concerns subsumption testing. We propose such second order extensions and evaluate their potential effectiveness with a number of experiments in subsumption as well as in query mining.

Implementing Query Completeness Reasoning

Data completeness is commonly regarded as one of the key aspects of data quality. With this paper we make two main contributions: (i) we develop techniques to reason about the completeness of a query answer over a partially complete database, taking into account constraints that hold over the database, and (ii) we implement them by an encoding into logic programming paradigms. As constraints we consider primary and foreign keys as well as finite domain constraints. In this way we can identify more situations in which a query is complete than was possible with previous work. For each combination of constraints, we establish characterizations of the completeness reasoning and we show how to translate them into logic programs. As a proof of concept we ran our encodings against test cases that capture characteristics of a real-world scenario.

Learning constraints in spreadsheets and tabular data

Spreadsheets, comma separated value files and other tabular data representations are in wide use today. However, writing, maintaining and identifying good formulas for tabular data and spreadsheets can be time-consuming and error-prone. We investigate the automatic learning of constraints (formulas and relations) in raw tabular data in an unsupervised way. We represent common spreadsheet formulas and relations through predicates and expressions whose arguments must satisfy the inherent properties of the constraint. The challenge is to automatically infer the set of constraints present in the data, without labeled examples or user feedback. We propose a two-stage generate and test method where the first stage uses constraint solving techniques to efficiently reduce the number of candidates, based on the predicate signatures. Our approach takes inspiration from inductive logic programming, constraint learning and constraint satisfaction. We show that we are able to accurately discover constraints in spreadsheets from various sources.

TaCLe: Learning Constraints in Tabular Data

Spreadsheet data is widely used today by many different people and across industries. However, writing, maintaining and identifying good formulae for spreadsheets can be time consuming and error-prone. To address this issue we have introduced the TaCLe system (Tabular Constraint Learner). The system tackles an inverse learning problem: given a plain comma separated file, it reconstructs the spreadsheet formulae that hold in the tables. Two important considerations are the number of cells and constraints to check, and how to deal with multiple formulae for the same cell. Our system reasons over entire rows and columns and has an intuitive user interface for interacting with the learned constraints and data. It can be seen as an intelligent assistance tool for discovering formulae from data. As a result, the user obtains a spreadsheet that can automatically recompute dependent cells when updating or adding data.

Modeling in MiningZinc

MiningZinc offers a framework for modeling and solving constraint-based mining problems. The language used is MiniZinc, a high-level declarative language for modeling combinatorial (optimisation) problems. This language is augmented with a library of functions and predicates that help modeling data mining problems and facilities for interfacing with databases. We show how MiningZinc can be used to model constraint-based itemset mining problems, for which it was originally designed, as well as sequence mining, Bayesian pattern mining, linear regression, clustering data factorization and ranked tiling. The underlying framework can use any existing MiniZinc solver. We also showcase how the framework and modeling capabilities can be integrated into an imperative language, for example as part of a greedy algorithm.