Spatial datasets are used extensively to train machine learning (ML) models for applications such as spatial regression, classification, clustering, and deep learning. Most of the real-world spatial datasets are often too large, and many spatial ML algorithms represent the geographical region as a grid consisting of several spatial cells. If the granularity of the grid is too fine, that results in a large number of grid cells leading to long training time and high memory consumption issues during the model training. To alleviate this problem, we propose a machine learning-aware spatial data re-partitioning framework that substantially reduces the granularity of the spatial grid. Our spatial data re-partitioning approach combines fine-grained, adjacent spatial cells from a grid into coarser cells prior to training an ML model. During this re-partitioning phase, we keep the information loss within a user-defined threshold without significantly degrading the accuracy of the ML model. According to the empirical evaluation performed on several real-world datasets, the best results achieved by our spatial re-partitioning framework show that we can reduce the data volume and training time by up to 81%, while keeping the difference in prediction or classification error below 5% as compared to a model that is trained on the original input dataset, for most of the ML applications. Our re-partitioned framework also outperforms the state-of-the-art data reduction baselines by 2% to 20% w.r.t. prediction and classification errors.

Identifying various mentions of the same real-world locations is known as spatial entity matching. GEM is an end-to-end Geospatial EM framework that matches polygon geometry entities in addition to point geometry type. Blocking, feature vector creation, and classification are the core steps of our system. GEM comprises of an efficient and lightweight blocking technique, GeoPrune, that uses the geohash encoding mechanism. We re-purpose the spatial proximality operators from Apache Sedona to create semantically rich spatial feature vectors. The classification step in GEM is a pluggable component, which consumes a unique feature vector and determines whether the geolocations match or not. We conduct experiments with three classifiers upon multiple large-scale geospatial datasets consisting of both spatial and relational attributes. GEM achieves an F-measure of 1.0 for a point x point dataset with 176k total pairs, which is 42% higher than a state-of-the-art spatial EM baseline. It achieves F-measures of 0.966 and 0.993 for the point x polygon dataset with 302M total pairs, and the polygon x polygon dataset with 16M total pairs respectively.

Prediction of the next SQL query from the user, given her sequence of queries until the current timestep, during an ongoing interaction session of the user with the database, can help in speculative query processing and increased interactivity. While existing machine learning-- (ML) based approaches use recommender systems to suggest relevant queries to a user, there has been no exhaustive study on applying temporal predictors to predict the next user issued query. In this work, we experimentally compare ML algorithms in predicting the immediate next future query in an interaction workload, given the current user query or the sequence of queries in a user session thus far. As a part of this, we propose the adaptation of two powerful temporal predictors: (a) Recurrent Neural Networks (RNNs) and (b) a Reinforcement Learning approach called Q-Learning that uses Markov Decision Processes. We represent each query as a comprehensive set of fragment embeddings that not only captures the SQL operators, attributes, and relations but also the arithmetic comparison operators and constants that occur in the query. Our experiments on two real-world datasets show the effectiveness of temporal predictors against the baseline recommender systems in predicting the structural fragments in a query w.r.t. both quality and time. Besides showing that RNNs can be used to synthesize novel queries, we find that exact Q-Learning outperforms RNNs despite predicting the next query entirely from the historical query logs.

Entity Matching (EM) is a core data cleaning task, aiming to identify different mentions of the same real-world entity. Active learning is one way to address the challenge of scarce labeled data in practice, by dynamically collecting the necessary examples to be labeled by an Oracle and refining the learned model (classifier) upon them. In this paper, we build a unified active learning benchmark framework for EM that allows users to easily combine different learning algorithms with applicable example selection algorithms. The goal of the framework is to enable concrete guidelines for practitioners as to what active learning combinations will work well for EM. Towards this, we perform comprehensive experiments on publicly available EM datasets from product and publication domains to evaluate active learning methods, using a variety of metrics including EM quality, #labels and example selection latencies. Our most surprising result finds that active learning with fewer labels can learn a classifier of comparable quality as supervised learning. In fact, for several of the datasets, we show that there is an active learning combination that beats the state-of-the-art supervised learning result. Our framework also includes novel optimizations that improve the quality of the learned model by roughly 9% in terms of F1-score and reduce example selection latencies by up to 10× without affecting the quality of the model.

We present RUDIK, a system for the discovery of declarative rules over knowledge-bases (KBs). RUDIK discovers rules that express positive relationships between entities, such as "if two persons have the same parent, they are siblings", and negative rules, i.e., patterns that identify contradictions in the data, such as "if two persons are married, one cannot be the child of the other". While the former class infers new facts in the KB, the latter class is crucial for other tasks, such as detecting erroneous triples in data cleaning, or the creation of negative examples to bootstrap learning algorithms. The system is designed to: (i) enlarge the expressive power of the rule language to obtain complex rules and wide coverage of the facts in the KB, (ii) discover approximate rules (soft constraints) to be robust to errors and incompleteness in the KB, (iii) use disk-based algorithms, effectively enabling rule mining in commodity machines. In contrast with traditional ranking of all rules based on a measure of support, we propose an approach to identify the subset of useful rules to be exposed to the user. We model the mining process as an incremental graph exploration problem and prove that our search strategy has guarantees on the optimality of the results. We have conducted extensive experiments using real-world KBs to show that RUDIK outperforms previous proposals in terms of efficiency and that it discovers more effective rules for the application at hand.

There has been an increasing interest into blurring the line between human-interaction and database systems. Several research papers tackled the Human-Database Interaction (HDI) challenge, yet none of them provides a holistic HDI approach. In this talk, we briefly describe dbTinder, a database engine that bridges the gap between the conversation approach humans use to interact and theQuery→Answerapproach used in classic database systems. To achieve that, dbTinder turns HDI into an intent discovery process where the system pro-actively converses with the user to guide her towards potentiallyinterestingtuples in the database.

RuDiK is a system for the discovery of declarative rules over knowledge-bases (KBs). RuDiK discovers both positive rules, which identify relationships between entities, e.g., "if two persons have the same parent, they are siblings", and negative rules, which identify data contradictions, e.g., "if two persons are married, one cannot be the child of the other". Rules help domain experts to curate data in large KBs. Positive rules suggest new facts to mitigate incompleteness and negative rules detect erroneous facts. Also, negative rules are useful to generate negative examples for learning algorithms. RuDiK goes beyond existing solutions since it discovers rules with a more expressive rule language w.r.t. previous approaches, which leads to wide coverage of the facts in the KB, and its mining is robust to existing errors and incompleteness in the KB. The system has been deployed for multiple KBs, including Yago, DBpedia, Freebase and Wiki-Data, and identifies new facts and real errors with 85% to 97% accuracy, respectively. This demonstration shows how RuDiK can be used to interact with domain experts. Once the audience pick a KB and a predicate, they will add new facts, remove errors, and train a machine learning system with automatically generated examples.

Entity matching (EM) is a critical part of data integration and cleaning. In many applications, the users need to understand why two entities are considered a match, which reveals the need for interpretable and concise EM rules. We model EM rules in the form of General Boolean Formulas (GBFs) that allows arbitrary attribute matching combined by conjunctions (∨), disjunctions (∧), and negations. (¬) GBFs can generate more concise rules than traditional EM rules represented in disjunctive normal forms (DNFs). We use program synthesis, a powerful tool to automatically generate rules (or programs) that provably satisfy a high-level specification, to automatically synthesize EM rules in GBF format, given only positive and negative matching examples.

Entity matching (EM) is a critical part of data integration. We study how to synthesize entity matching rules from positive-negative matching examples. The core of our solution is program synthesis , a powerful tool to automatically generate rules (or programs) that satisfy a given high-level specification, via a predefined grammar. This grammar describes a General Boolean Formula ( GBF ) that can include arbitrary attribute matching predicates combined by conjunctions (∧), disjunctions (∨) and negations (¬), and is expressive enough to model EM problems, from capturing arbitrary attribute combinations to handling missing attribute values. The rules in the form of GBF are more concise than traditional EM rules represented in Disjunctive Normal Form ( DNF ). Consequently, they are more interpretable than decision trees and other machine learning algorithms that output deep trees with many branches. We present a new synthesis algorithm that, given only positive-negative examples as input, synthesizes EM rules that are effective over the entire dataset. Extensive experiments show that we outperform other interpretable rules (e.g., decision trees with low depth) in effectiveness, and are comparable with non-interpretable tools (e.g., decision trees with high depth, gradient-boosting trees, random forests and SVM).