Localizing video moments based on the movement patterns of objects is an important task in video analytics. Existing video analytics systems offer two types of querying interfaces based on natural language and SQL, respectively. However, both types of interfaces have major limitations. SQL-based systems require high query specification time, whereas natural language-based systems require large training datasets to achieve satisfactory retrieval accuracy. To address these limitations, we present SketchQL, a video database management system (VDBMS) for offline, exploratory video moment retrieval that is both easy to use and generalizes well across multiple video moment datasets. To improve ease-of-use, SketchQL features a visual query interface that enables users to sketch complex visual queries through intuitive drag-and-drop actions. To improve generalizability, SketchQL operates on object-tracking primitives that are reliably extracted across various datasets using pre-trained models. We present a learned similarity search algorithm for retrieving video moments closely matching the user's visual query based on object trajectories. SketchQL trains the model on a diverse dataset generated with a novel simulator, that enhances its accuracy across a wide array of datasets and queries. We evaluate SketchQL on four real-world datasets with nine queries, demonstrating its superior usability and retrieval accuracy over state-of-the-art VDBMSs.

In this paper, we will present SketchQL, a video database management system (VDBMS) for retrieving video moments with a sketch-based query interface. This novel interface allows users to specify object trajectory events with simple mouse drag-and-drop operations. Users can use trajectories of single objects as building blocks to compose complex events. Using a pre-trained model that encodes trajectory similarity, SketchQL achieves zero-shot video moments retrieval by performing similarity searches over the video to identify clips that are the most similar to the visual query. In this demonstration, we introduce the graphic user interface of SketchQL and detail its functionalities and interaction mechanisms. We also demonstrate the end-to-end usage of SketchQL from query composition to video moments retrieval using real-world scenarios.

Data preprocessing is a crucial step in the machine learning process that transforms raw data into a more usable format for downstream ML models. However, it can be costly and time-consuming, often requiring the expertise of domain experts. Existing automated machine learning (AutoML) frameworks claim to automate data preprocessing. However, they often use a restricted search space of data preprocessing pipelines which limits the potential performance gains, and they are often too slow as they require training the ML model multiple times. In this paper, we propose DiffPrep, a method that can automatically and efficiently search for a data preprocessing pipeline for a given tabular dataset and a differentiable ML model such that the performance of the ML model is maximized. We formalize the problem of data preprocessing pipeline search as a bi-level optimization problem. To solve this problem efficiently, we transform and relax the discrete, non-differential search space into a continuous and differentiable one, which allows us to perform the pipeline search using gradient descent with training the ML model only once. Our experiments show that DiffPrep achieves the best test accuracy on 15 out of the 18 real-world datasets evaluated and improves the model's test accuracy by up to 6.6 percentage points.

Entity matching (EM) refers to the problem of identifying pairs of data records in one or more relational tables that refer to the same entity in the real world. Supervised machine learning (ML) models currently achieve state-of-the-art matching performance; however, they require a large number of labeled examples, which are often expensive or infeasible to obtain. This has inspired us to approach data labeling for EM using weak supervision. In particular, we use the labeling function abstraction popularized by Snorkel, where each labeling function (LF) is a user-provided program that can generate many noisy match/non-match labels quickly and cheaply. Given a set of user-written LFs, the quality of data labeling depends on a labeling model to accurately infer the ground-truth labels. In this work, we first propose a simple but powerful labeling model for general weak supervision tasks. Then, we tailor the labeling model specifically to the task of entity matching by considering the EM-specific transitivity property. The general form of our labeling model is simple while substantially outperforming the best existing method across ten general weak supervision datasets. To tailor the labeling model for EM, we formulate an approach to ensure that the final predictions of the labeling model satisfy the transitivity property required in EM, utilizing an exact solution where possible and an ML-based approximation in remaining cases. On two single-table and nine two-table real-world EM datasets, we show that our labeling model results in a 9% higher F1 score on average than the best existing method. We also show that a deep learning EM end model (DeepMatcher) trained on labels generated from our weak supervision approach is comparable to an end model trained using tens of thousands of ground-truth labels, demonstrating that our approach can significantly reduce the labeling efforts required in EM.

As machine learning becomes prevalent, mitigating any unfairness present in the training data becomes critical. Among the various notions of fairness, this paper focuses on the well-known individual fairness, which states that similar individuals should be treated similarly. While individual fairness can be improved when training a model (in-processing), we contend that fixing the data before model training (pre-processing) is a more fundamental solution. In particular, we show that label flipping is an effective pre-processing technique for improving individual fairness. Our system iFlipper solves the optimization problem of minimally flipping labels given a limit to the individual fairness violations, where a violation occurs when two similar examples in the training data have different labels. We first prove that the problem is NP-hard. We then propose an approximate linear programming algorithm and provide theoretical guarantees on how close its result is to the optimal solution in terms of the number of label flips. We also propose techniques for making the linear programming solution more optimal without exceeding the violations limit. Experiments on real datasets show that iFlipper significantly outperforms other pre-processing baselines in terms of individual fairness and accuracy on unseen test sets. In addition, iFlipper can be combined with in-processing techniques for even better results.

Most real-world datasets contain label noise, which can negatively affect downstream ML models trained on them. To deal with this problem, one can clean the mislabeled data before training, which is not only time-consuming and expensive but also requires domain expertise. Another approach is to use a noise-robust ML training algorithm. However, existing methods have some prerequisites that may not be practical in many applications (e.g., they are tied to specific downstream model architecture or they are applicable to specific noise distributions). In this paper, we propose a model-agnostic approach for learning with noisy labels of arbitrary distributions. In particular, our approach can work with any gradient descent optimization based machine learning model and deal with any label noise distribution. We achieve them by proposing two theoretically grounded noise-robust loss functions (for different noise distributions), and we are able to automatically decide which loss function to use based on a novel noise setting detection module. We directly learn the required hyper-parameters in the loss functions via meta-learning technique to minimize the loss on a given small clean validation set, and propose several strategies to improve the efficiency of training. Experiments on multiple datasets with both real-world and injected label noise show that our method performs better than state-of-the-art approaches.

Data quality affects machine learning (ML) model performances, and data scientists spend considerable amount of time on data cleaning before model training. However, to date, there does not exist a rigorous study on how exactly cleaning affects ML - ML community usually focuses on developing ML algorithms that are robust to some particular noise types of certain distributions, while database (DB) community has been mostly studying the problem of data cleaning alone without considering how data is consumed by downstream ML analytics.We propose a CleanML study that systematically investigates the impact of data cleaning on ML classification tasks. The open-source and extensible CleanML study currently includes 14 real-world datasets with real errors, five common error types, seven different ML models, and multiple cleaning algorithms for each error type (including both commonly used algorithms in practice as well as state-of-the-art solutions in academic literature). We control the randomness in ML experiments using statistical hypothesis testing, and we also control false discovery rate in our experiments using the Benjamini-Yekutieli (BY) procedure. We analyze the results in a systematic way to derive many interesting and nontrivial observations. We also put forward multiple research directions for researchers.

Fuzzy similarity join is an important database operator widely used in practice. So far the research community has focused exclusively on optimizing fuzzy joinscalability. However, practitioners today also struggle to optimize fuzzy-joinquality, because they face a daunting space of parameters (e.g., distance-functions, distance-thresholds, tokenization-options, etc.), and often have to resort to a manual trial-and-error approach to program these parameters in order to optimize fuzzy-join quality. This key challenge of automatically generating high-quality fuzzy-join programs has received surprisingly little attention thus far. In this work, we study the problem of "auto-program'' fuzzy-joins. Leveraging a geometric interpretation of distance-functions, we develop an unsupervised Auto-FuzzyJoin framework that can infer suitable fuzzy-join programs on given input tables, without requiring explicit human input such as labelled training data. Using Auto-FuzzyJoin, users only need to provide two input tables L and R, and a desired precision target τ (say 0.9). Auto-FuzzyJoin leverages the fact that one of the input is a reference table to automatically program fuzzy-joins that meet the precision target τ in expectation, while maximizing fuzzy-join recall (defined as the number of correctly joined records). Experiments on both existing benchmarks and a new benchmark with 50 fuzzy-join tasks created from Wikipedia data suggest that the proposed Auto-FuzzyJoin significantly outperforms existing unsupervised approaches, and is surprisingly competitive even against supervised approaches (e.g., Magellan and DeepMatcher) when 50% of ground-truth labels are used as training data. We have released our code and benchmark on GitHub\footnote\urlhttps://github.com/chu-data-lab/AutomaticFuzzyJoin to facilitate future research.

Machine learning (ML) is increasingly being used to make decisions in our society. ML models, however, can be unfair to certain demographic groups (e.g., African Americans or females) according to various fairness metrics. Existing techniques for producing fair ML models either are limited to the type of fairness constraints they can handle (e.g., preprocessing) or require nontrivial modifications to downstream ML training algorithms (e.g., in-processing).

Estimating the number of distinct values (NDV) in a column is useful for many tasks in database systems, such as columnstore compression and data profiling. In this work, we focus on how to derive accurate NDV estimations from random (online/offline) samples. Such efficient estimation is critical for tasks where it is prohibitive to scan the data even once. Existing sample-based estimators typically rely on heuristics or assumptions and do not have robust performance across different datasets as the assumptions on data can easily break. On the other hand, deriving an estimator from a principled formulation such as maximum likelihood estimation is very challenging due to the complex structure of the formulation. We propose to formulate the NDV estimation task in a supervised learning framework, and aim to learn a model as the estimator. To this end, we need to answer several questions: i) how to make the learned model workload agnostic; ii) how to obtain training data; iii) how to perform model training. We derive conditions of the learning framework under which the learned model isworkload agnostic, in the sense that the model/estimator can be trained with synthetically generated training data, and then deployed into any data warehouse simply as,e.g., user-defined functions (UDFs), to offer efficient (within microseconds on CPU) and accurate NDV estimations forunseen tables and workloads.We compare the learned estimator with the state-of-the-art sample-based estimators on nine real-world datasets to demonstrate its superior estimation accuracy. We publish our code for training data generation, model training, and the learned estimator online for reproducibility.

Entity matching (EM) refers to the problem of identifying tuple pairs in one or more relations that refer to the same real world entities. Supervised machine learning (ML) approaches, and deep learning based approaches in particular, typically achieve state-of-the-art matching results. However, these approaches require many labeled examples, in the form of matching and non-matching pairs, which are expensive and time-consuming to label. In this paper, we introduce Panda, a weakly supervised system specifically designed for EM. Panda uses the same labeling function abstraction as Snorkel, where labeling functions (LF) are user-provided programs that can generate large amounts of (somewhat noisy) labels quickly and cheaply, which can then be combined via a labeling model to generate accurate final predictions. To support users developing LFs for EM, Panda provides an integrated development environment (IDE) that lives in a modern browser architecture. Panda's IDE facilitates the development, debugging, and life-cycle management of LFs in the context of EM tasks, similar to how IDEs such as Visual Studio or Eclipse excel in general-purpose programming. Panda's IDE includes many novel features purpose-built for EM, such as smart data sampling, a builtin library of EM utility functions, automatically generated LFs, visual debugging of LFs, and finally, an EM-specific labeling model. We show in this demo that Panda IDE can greatly accelerate the development of high-quality EM solutions using weak supervision.

Generating large labeled training data is becoming the biggest bottleneck in building and deploying supervised machine learning models. Recently, the data programming paradigm has been proposed to reduce the human cost in labeling training data. However, data programming relies on designing labeling functions which still requires significant domain expertise. Also, it is prohibitively difficult to write labeling functions for image datasets as it is hard to express domain knowledge using raw features for images (pixels). We propose affinity coding, a new domain-agnostic paradigm for automated training data labeling. The core premise of affinity coding is that the affinity scores of instance pairs belonging to the same class on average should be higher than those of pairs belonging to different classes, according to some affinity functions. We build the GOGGLES system that implements affinity coding for labeling image datasets by designing a novel set of reusable affinity functions for images, and propose a novel hierarchical generative model for class inference using a small development set. We compare GOGGLES with existing data programming systems on 5 image labeling tasks from diverse domains. GOGGLES achieves labeling accuracies ranging from a minimum of 71% to a maximum of 98% without requiring any extensive human annotation. In terms of end-to-end performance, GOGGLES outperforms the state-of-the-art data programming system Snuba by 21% and a state-of-the-art few-shot learning technique by 5%, and is only 7% away from the fully supervised upper bound.

Entity resolution (ER) refers to the problem of matching records in one or more relations that refer to the same real-world entity. While supervised machine learning (ML) approaches achieve the state-of-the-art results, they require a large amount of labeled examples that are expensive to obtain and often times infeasible. We investigate an important problem that vexes practitioners: is it possible to design an effective algorithm for ER that requires Zero labeled examples, yet can achieve performance comparable to supervised approaches? In this paper, we answer in the affirmative through our proposed approach dubbed ZeroER. Our approach is based on a simple observation --- the similarity vectors for matches should look different from that of unmatches. Operationalizing this insight requires a number of technical innovations. First, we propose a simple yet powerful generative model based on Gaussian Mixture Models for learning the match and unmatch distributions. Second, we propose an adaptive regularization technique customized for ER that ameliorates the issue of feature overfitting. Finally, we incorporate the transitivity property into the generative model in a novel way resulting in improved accuracy. On five benchmark ER datasets, we show that ZeroER greatly outperforms existing unsupervised approaches and achieves comparable performance to supervised approaches.

Machine learning (ML) applications have been thriving recently, largely attributed to the increasing availability of data. However, inconsistency and incomplete information are ubiquitous in real-world datasets, and their impact on ML applications remains elusive. In this paper, we present a formal study of this impact by extending the notion of Certain Answers for Codd tables , which has been explored by the database research community for decades, into the field of machine learning. Specifically, we focus on classification problems and propose the notion of "Certain Predictions" (CP) --- a test data example can be certainly predicted (CP'ed) if all possible classifiers trained on top of all possible worlds induced by the incompleteness of data would yield the same prediction. We study two fundamental CP queries: (Q1) checking query that determines whether a data example can be CP'ed; and (Q2) counting query that computes the number of classifiers that support a particular prediction (i.e., label). Given that general solutions to CP queries are, not surprisingly, hard without assumption over the type of classifier, we further present a case study in the context of nearest neighbor (NN) classifiers, where efficient solutions to CP queries can be developed --- we show that it is possible to answer both queries in linear or polynomial time over exponentially many possible worlds. We demonstrate one example use case of CP in the important application of "data cleaning for machine learning (DC for ML)." We show that our proposed CPClean approach built based on CP can often significantly outperform existing techniques, particularly on datasets with systematic missing values. For example, on 5 datasets with systematic missingness, CPClean (with early termination) closes 100% gap on average by cleaning 36% of dirty data on average, while the best automatic cleaning approach BoostClean can only close 14% gap on average.

With the dramatic increasing interest in data analysis, ensuring data quality becomes one of the most important topics in data science. Data Cleaning, the process of ensuring data quality, is composed of two stages: error detection and error repair. Despite decades of research in data cleaning, existing cleaning systems still have limitations in terms of usability and error coverage. We propose PIClean, a probabilistic and interactive data cleaning system that aims at addressing the aforementioned limitations. PIClean produces probabilistic errors and probabilistic fixes using low-rank approximation, which implicitly discovers and uses relationships between columns of a dataset for cleaning. The probabilistic errors and fixes are confirmed or rejected by users, and the user feedbacks are constantly incorporated by PIClean to produce more accurate and higher-coverage cleaning results.

Business analysts and data scientists today increasingly need to clean, standardize and transform diverse data sets, such as name, address, date time, phone number, etc., before they can perform analysis. These ad-hoc transformation problems are typically solved by one-off scripts, which is both difficult and time-consuming.

Today, business analysts and data scientists increasingly need to clean, standardize and transform diverse data sets, such as name, address, date time, and phone number, before they can perform analysis. This process of data transformation is an important part of data preparation, and is known to be difficult and time-consuming for end-users. Traditionally, developers have dealt with these longstanding transformation problems using custom code libraries. They have built vast varieties of custom logic for name parsing and address standardization, etc., and shared their source code in places like GitHub. Data transformation would be a lot easier for end-users if they can discover and reuse such existing transformation logic. We developed Transform-Data-by-Example ( TDE ), which works like a search engine for data transformations. TDE "indexes" vast varieties of transformation logic in source code, DLLs, web services and mapping tables, so that users only need to provide a few input/output examples to demonstrate a desired transformation, and TDE can interactively find relevant functions to synthesize new programs consistent with all examples. Using an index of 50K functions crawled from GitHub and Stackoverflow, TDE can already handle many common transformations not currently supported by existing systems. On a benchmark with over 200 transformation tasks, TDE generates correct transformations for 72% tasks, which is considerably better than other systems evaluated. A beta version of TDE for Microsoft Excel is available via Office store 1 . Part of the TDE technology also ships in Microsoft Power BI.

It is well known today that pages on the Web contain a large number of content-rich relational tables. Such tables have been systematically extracted in a number of efforts to empower important applications such as table search and schema discovery. However, a significant fraction of relational tables are not embedded in the standard HTML table tags, and are thus difficult to extract. In particular, a large number of relational tables are known to be in a ``list'' form, which contains a list of clearly separated rows that are not separated into columns.

Join is a powerful operator that combines records from two or more tables, which is of fundamental importance in the field of relational database. However, traditional join processing mostly relies on string equality comparisons. Given the growing demand for ad-hoc data analysis, we have seen an increasing number of scenarios where the desired join relationship is not equi-join. For example, in a spreadsheet environment, a user may want to join one table with a subject column country-name, with another table with a subject column country-code. Traditional equi-join cannot handle such joins automatically, and the user typically has to manually find an intermediate mapping table in order to perform the desired join. We develop a SEMA-JOIN approach that is a first step toward allowing users to perform semantic join automatically, with a click of the button. Our main idea is to utilize a data-driven method that leverages a big table corpus with over 100 million tables to determine statistical correlation between cell values at both row-level and column-level. We use the intuition that the correct join mapping is the one that maximizes aggregate pairwise correlation, to formulate the join prediction problem as an optimization problem. We develop a linear program relaxation and a rounding argument to obtain a 2-approximation algorithm in polynomial time. Our evaluation using both public tables from the Web and proprietary Enterprise tables from a large company shows that the proposed approach can perform automatic semantic joins with high precision for a variety of common join scenarios.