A large body of machine learning and AI is focused on learning models composed of (probabilistic) logical rules, i.e., relational models, over relational databases and knowledge bases. To learn effective relational models over the huge space of possible ones efficiently, users of the current learning systems must restrict the structure of the candidate models using language bias. ML experts have to spend a long time inspecting the data and performing many rounds of trial and error to develop an effective language bias. We propose AutoBias, a system that leverages information in the underlying data to generate the language bias. As its induced language bias may not restrict the set of candidate models as tightly as the manually-written ones, learning may not scale to large datasets. Thus, we design novel and efficient methods to sample and learn effective relational models over large data. Our extensive empirical study shows that AutoBias delivers the same accuracy as using manually-written language bias by imposing only a slight overhead on the learning time.

Real-world datasets are dirty and contain many errors, such as violations of integrity constraints and entity duplicates. Learning over dirty databases may result in inaccurate models. Data scientists spend most of their time on preparing and repairing data errors to create clean databases for learning. Moreover, as the information required to repair these errors is not often available, there may be numerous possible clean versions for a dirty database. We propose Dirty Learn, DLearn, a novel learning system that learns directly over dirty databases effectively and efficiently without any preprocessing. DLearn leverages database constraints to learn accurate relational models over inconsistent and heterogeneous data. Its learned models represent patterns over all possible clean versions of the data in a usable form. Our empirical study indicates that DLearn learns accurate models over large real-world databases efficiently.

Relational learning algorithms learn the Datalog definition of novel relations in terms of existing relations in the database. In order to effectively use these algorithms, users must constraint the space of candidate definitions by specifying a language bias. Unfortunately, specifying the language bias takes a great deal of time and effort, as it is done via trial and error and is guided by the expert's intuitions. We demonstrate AutoMode, a system that leverages information in the schema and content of the database to automatically induce the language bias used by popular relational learning algorithms.

Public cloud database providers observe all sorts of different usage patterns and behaviors while operating their services. Service providers such as Microsoft try to understand and characterize these behaviors in order to improve the quality of their service, provide new features for customers, and/or increase the efficiency of the operations. While there are many types of patterns of behavior that are of interest to providers, such as query types, workload intensity, and temporal activity, in this paper, we focus on the lowest level of behavior -- how long do public cloud databases survive before being dropped? Given the large and diverse relational database population that Azure SQL DB has, we present a large-scale survivability study of our service and identify some factors that can demonstrably help predict the lifespan of cloud databases. The results of this study are being used to influence how Azure SQL DB operates in order to increase efficiency as well as improve customer experience.

Given a relational database and training examples for a target relation, relational learning algorithms learn a Datalog program that defines the target relation in terms of the existing relations in the database. We demonstrate CastorX, a relational learning system that performs relational learning over heterogeneous databases. The user specifies matching attributes between (heterogeneous) databases through matching dependencies. Because the content in these attributes may not match exactly, CastorX uses similarity operators to find matching values in these attributes. As the learning process may become expensive, CastorX implements sampling techniques that allow it to learn efficiently and output accurate definitions.

Learning novel relations from relational databases is an important problem with many applications. Relational learning algorithms learn the definition of a new relation in terms of existing relations in the database. Nevertheless, the same database may be represented under different schemas for various reasons, such as data quality, efficiency and usability. The output of current relational learning algorithms tends to vary quite substantially over the choice of schema. This variation complicates their off-the-shelf application. We introduce and formalize the property of schema independence of relational learning algorithms, and study both the theoretical and empirical dependence of existing algorithms on the common class of (de) composition schema transformations. We show that current algorithms are not schema independent. We propose Castor, a relational learning algorithm that achieves schema independence by leveraging data dependencies.

Learning novel relations from relational databases is an important problem with many applications in database systems and machine learning. Relational learning algorithms leverage the properties of the database schema to find the definition of the target relation in terms of the existing relations in the database. However, the same data set may be represented under different schemas for various reasons, such as efficiency and data quality. Unfortunately, current relational learning algorithms tend to vary quite substantially over the choice of schema, which complicates their off-the-shelf application. We demonstrate Castor , a relational learning system that efficiently learns the same definitions over common schema variations. The results of Castor are more accurate than well-known learning systems over large data.