Certain and Approximately Certain Models for Statistical Learning

Real-world data is often incomplete and contains missing values. To train accurate models over real-world datasets, users need to spend a substantial amount of time and resources imputing and finding proper values for missing data items. In this paper, we demonstrate that it is possible to learn accurate models directly from data with missing values for certain training data and target models. We propose a unified approach for checking the necessity of data imputation to learn accurate models across various widely-used machine learning paradigms. We build efficient algorithms with theoretical guarantees to check this necessity and return accurate models in cases where imputation is unnecessary. Our extensive experiments indicate that our proposed algorithms significantly reduce the amount of time and effort needed for data imputation without imposing considerable computational overhead.

Towards Consistent Language Models Using Declarative Constraints

Large language models have shown unprecedented abilities in generating linguistically coherent and syntactically correct natural language output. However, they often return incorrect and inconsistent answers to input questions. Due to the complexity and uninterpretability of the internally learned representations, it is challenging to modify language models such that they provide correct and consistent results. The data management community has developed various methods and tools for providing consistent answers over inconsistent datasets. In these methods, users specify the desired properties of data in a domain in the form of high-level declarative constraints. This approach has provided usable and scalable methods to delivering consistent information from inconsistent datasets. We aim to build upon this success and leverage these methods to modify language models such that they deliver consistent and accurate results. We investigate the challenges of using these ideas to obtain consistent and relevant answers from language models and report some preliminary empirical studies.

Learning Over Dirty Data Without Cleaning

Real-world datasets are dirty and contain many errors. Examples of these issues are violations of integrity constraints, duplicates, and inconsistencies in representing data values and entities. Learning over dirty databases may result in inaccurate models. Users have to spend a great deal of time and effort to repair data errors and create a clean database 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 DLearn, a novel relational 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 instances of the data in a usable form. Our empirical study indicates that DLearn learns accurate models over large real-world databases efficiently.

A Signaling Game Approach to Databases Querying and Interaction

As most users do not precisely know the structure and/or the content of databases, their queries do not exactly reflect their information needs. The database management systems (DBMS) may interact with users and use their feedback on the returned results to learn the information needs behind their queries. Current query interfaces assume that users do not learn and modify the way way they express their information needs in form of queries during their interaction with the DBMS. Using a real-world interaction workload, we show that users learn and modify how to express their information needs during their interactions with the DBMS and their learning is accurately modeled by a well-known reinforcement learning mechanism. As current data interaction systems assume that users do not modify their strategies, they cannot discover the information needs behind users' queries effectively. We model the interaction between users and DBMS as a game with identical interest between two rational agents whose goal is to establish a common language for representing information needs in form of queries. We propose a reinforcement learning method that learns and answers the information needs behind queries and adapts to the changes in users' strategies and prove that it improves the effectiveness of answering queries stochastically speaking. We propose two efficient implementation of this method over large relational databases. Our extensive empirical studies over real-world query workloads indicate that our algorithms are efficient and effective.

Schema Independent Relational Learning

Learning novel concepts and relations from relational databases is an important problem with many applications in database systems and machine learning. Relational learning algorithms learn the definition of a new relation in terms of existing relations in the database. Nevertheless, the same data set may be represented under different schemas for various reasons, such as efficiency, data quality, and usability. Unfortunately, the output of current relational learning algorithms tends to vary quite substantially over the choice of schema, both in terms of learning accuracy and efficiency. This variation complicates their off-the-shelf application. In this paper, 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 study both sample-based learning algorithms, which learn from sets of labeled examples, and query-based algorithms, which learn by asking queries to an oracle. We prove that current relational learning algorithms are generally not schema independent. For query-based learning algorithms we show that the (de) composition transformations influence their query complexity. We propose Castor, a sample-based relational learning algorithm that achieves schema independence by leveraging data dependencies. We support the theoretical results with an empirical study that demonstrates the schema dependence/independence of several algorithms on existing benchmark and real-world datasets under (de) compositions.

AutoMode: Relational Learning With Less Black Magic

Relational databases are valuable resources for learning novel and interesting relations and concepts. Relational learning algorithms learn the Datalog definition of new relations in terms of the existing relations in the database. In order to constraint the search through the large space of candidate definitions, users must tune the algorithm by specifying a language bias. Unfortunately, specifying the language bias is done via trial and error and is guided by the expert's intuitions. Hence, it normally takes a great deal of time and effort to effectively use these algorithms. In particular, it is hard to find a user that knows computer science concepts, such as database schema, and has a reasonable intuition about the target relation in special domains, such as biology. We propose 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 systems. We show that AutoMode delivers the same accuracy as using manually-written language bias by imposing only a slight overhead on the running time of the learning algorithm.