Eugene Wu
Comparison is a core task in visual analysis. Although there are numerous guidelines to help users design effective visualizations to aid known comparison tasks, there are few techniques available when users want to make ad hoc comparisons between marks, trends, or charts during data exploration and visual analysis. For instance, to compare voting count maps from different years, two stock trends in a line chart, or a scatterplot of country GDPs with a textual summary of the average GDP. Ideally, users can directly select the comparison targets and compare them, however what elements of a visualization should be candidate targets, which combinations of targets are safe to compare, and what comparison operations make sense? This paper proposes a conceptual model that lets users compose combinations of values, marks, legend elements, and charts using a set of composition operators that summarize, compute differences, merge, and model their operands. We further define a View Composition Algebra (VCA) that is compatible with datacube-based visualizations, derive an interaction design based on this algebra that supports ad hoc visual comparisons, and illustrate its utility through several use cases.
Qianrui Zhang, Haoci Zhang, Thibault Sellam, Eugene Wu
Interactive tools make data analysis more efficient and more accessible to end-users by hiding the underlying query complexity and exposing interactive widgets for the parts of the query that matter to the analysis. However, creating custom tailored (i.e., precise) interfaces is very costly, and automated approaches are desirable. We propose a syntactic approach that uses queries from an analysis to generate a tailored interface. We model interface widgets as functions I(q) -> q' that modify the current analysis query $q$, and interfaces as the set of queries that its widgets can express. Our system, Precision Interfaces, analyzes structural changes between input queries from an analysis, and generates an output interface with widgets to express those changes. Our experiments on the Sloan Digital Sky Survey query log suggest that Precision Interfaces can generate useful interfaces for simple unanticipated tasks, and our optimizations can generate interfaces from logs of up to 10,000 queries in <10s.
Hamed Nilforoshan, Eugene Wu
User-generated, multi-paragraph writing is pervasive and important in many social media platforms (i.e. Amazon reviews, AirBnB host profiles, etc). Ensuring high-quality content is important. Unfortunately, content submitted by users is often not of high quality. Moreover, the characteristics that constitute high quality may even vary between domains in ways that users are unaware of. Automated writing feedback has the potential to immediately point out and suggest improvements during the writing process. Most approaches, however, focus on syntax/phrasing, which is only one characteristic of high-quality content. Existing research develops accurate quality prediction models. We propose combining these models with model explanation techniques to identify writing features that, if changed, will most improve the text quality. To this end, we develop a perturbation-based explanation method for a popular class of models called tree-ensembles. Furthermore, we use a weak-supervision technique to adapt this method to generate feedback for specific text segments in addition to feedback for the entire document. Our user study finds that the perturbation-based approach, when combined with segment-specific feedback, can help improve writing quality on Amazon (review helpfulness) and Airbnb (host profile trustworthiness) by > 14% (3X improvement over recent automated feedback techniques).
Hamed Nilforoshan, Jiannan Wang, Eugene Wu
Quality control in crowdsourcing systems is crucial. It is typically done after data collection, often using additional crowdsourced tasks to assess and improve the quality. These post-hoc methods can easily add cost and latency to the acquisition process--particularly if collecting high-quality data is important. In this paper, we argue for pre-hoc interface optimizations based on feedback that helps workers improve data quality before it is submitted and is well suited to complement post-hoc techniques. We propose the Precog system that explicitly supports such interface optimizations for common integrity constraints as well as more ambiguous text acquisition tasks where quality is ill-defined. We then develop the Segment-Predict-Explain pattern for detecting low-quality text segments and generating prescriptive explanations to help the worker improve their text input. Our unique combination of segmentation and prescriptive explanation are necessary for Precog to collect 2x more high-quality text data than non-Precog approaches on two real domains.
Haoci Zhang, Thibault Sellam, Eugene Wu
Interactive tools make data analysis both more efficient and more accessible to a broad population. Simple interfaces such as Google Finance as well as complex visual exploration interfaces such as Tableau are effective because they are tailored to the desired user tasks. Yet, designing interactive interfaces requires technical expertise and domain knowledge. Experts are scarce and expensive, and therefore it is currently infeasible to provide tailored (or precise) interfaces for every user and every task. We envision a data-driven approach to generate tailored interactive interfaces. We observe that interactive interfaces are designed to express sets of programs; thus, samples of programs-increasingly collected by data systems-may help us build interactive interfaces. Based on this idea, Precision Interfaces is a language-agnostic system that examines an input query log, identifies how the queries structurally change, and generates interactive web interfaces to express these changes. The focus of this paper is on applying this idea towards logs of structured queries. Our experiments show that Precision Interfaces can support multiple query languages (SQL and SPARQL), derive Tableau's salient interaction components from OLAP queries, analyze <75k queries in <12 minutes, and generate interaction designs that improve upon existing interfaces and are comparable to human-crafted interfaces.
Gabriel Ryan, Abigail Mosca, Remco Chang, Eugene Wu
When inspecting information visualizations under time critical settings, such as emergency response or monitoring the heart rate in a surgery room, the user only has a small amount of time to view the visualization "at a glance". In these settings, it is important to provide a quantitative measure of the visualization to understand whether or not the visualization is too "complex" to accurately judge at a glance. This paper proposes Pixel Approximate Entropy (PAE), which adapts the approximate entropy statistical measure commonly used to quantify regularity and unpredictability in time-series data, as a measure of visual complexity for line charts. We show that PAE is correlated with user-perceived chart complexity, and that increased chart PAE correlates with reduced judgement accuracy. We also find that the correlation between PAE values and participants' judgment increases when the user has less time to examine the line charts.
Eugene Wu, Xiang Yu Tuang, Antonio Li, Vareesh Bainwala
Existing data visualization formalisms are restricted to single-table inputs, which makes existing visualization grammars like Vega-lite or ggplot2 tedious to use, have overly complex APIs, and unsound when visualization multi-table data. This paper presents the first visualization formalism to support databases as input -- in other words, *database visualization*. A visualization specification is defined as a mapping from database constraints (e.g., schemas, types, foreign keys) to visual representations of those constraints, and we state that a visualization is *faithful* if it visually preserves the underlying database constraints. This formalism explains how visualization designs are the result of implicit data modeling decisions. We further develop a javascript library called dvl and use a series of case studies to show its expressiveness over specialized visualization systems and existing grammar-based languages.
Daniel Haas, Jiannan Wang, Eugene Wu, Michael J. Franklin
Data labeling is a necessary but often slow process that impedes the development of interactive systems for modern data analysis. Despite rising demand for manual data labeling, there is a surprising lack of work addressing its high and unpredictable latency. In this paper, we introduce CLAMShell, a system that speeds up crowds in order to achieve consistently low-latency data labeling. We offer a taxonomy of the sources of labeling latency and study several large crowd-sourced labeling deployments to understand their empirical latency profiles. Driven by these insights, we comprehensively tackle each source of latency, both by developing novel techniques such as straggler mitigation and pool maintenance and by optimizing existing methods such as crowd retainer pools and active learning. We evaluate CLAMShell in simulation and on live workers on Amazon's Mechanical Turk, demonstrating that our techniques can provide an order of magnitude speedup and variance reduction over existing crowdsourced labeling strategies.
Sanjay Krishnan, Eugene Wu
The analyst effort in data cleaning is gradually shifting away from the design of hand-written scripts to building and tuning complex pipelines of automated data cleaning libraries. Hyper-parameter tuning for data cleaning is very different than hyper-parameter tuning for machine learning since the pipeline components and objective functions have structure that tuning algorithms can exploit. This paper proposes a framework, called AlphaClean, that rethinks parameter tuning for data cleaning pipelines. AlphaClean provides users with a rich library to define data quality measures with weighted sums of SQL aggregate queries. AlphaClean applies generate-then-search framework where each pipelined cleaning operator contributes candidate transformations to a shared pool. Asynchronously, in separate threads, a search algorithm sequences them into cleaning pipelines that maximize the user-defined quality measures. This architecture allows AlphaClean to apply a number of optimizations including incremental evaluation of the quality measures and learning dynamic pruning rules to reduce the search space. Our experiments on real and synthetic benchmarks suggest that AlphaClean finds solutions of up-to 9x higher quality than naively applying state-of-the-art parameter tuning methods, is significantly more robust to straggling data cleaning methods and redundancy in the data cleaning library, and can incorporate state-of-the-art cleaning systems such as HoloClean as cleaning operators.
Sanjay Krishnan, Michael J. Franklin, Ken Goldberg, Eugene Wu
Predictive models based on machine learning can be highly sensitive to data error. Training data are often combined with a variety of different sources, each susceptible to different types of inconsistencies, and new data streams during prediction time, the model may encounter previously unseen inconsistencies. An important class of such inconsistencies is domain value violations that occur when an attribute value is outside of an allowed domain. We explore automatically detecting and repairing such violations by leveraging the often available clean test labels to determine whether a given detection and repair combination will improve model accuracy. We present BoostClean which automatically selects an ensemble of error detection and repair combinations using statistical boosting. BoostClean selects this ensemble from an extensible library that is pre-populated general detection functions, including a novel detector based on the Word2Vec deep learning model, which detects errors across a diverse set of domains. Our evaluation on a collection of 12 datasets from Kaggle, the UCI repository, real-world data analyses, and production datasets that show that Boost- Clean can increase absolute prediction accuracy by up to 9% over the best non-ensembled alternatives. Our optimizations including parallelism, materialization, and indexing techniques show a 22.2x end-to-end speedup on a 16-core machine.
Eugene Wu, Remco Chang
In visualization, the process of transforming raw data into visually comprehensible representations is pivotal. While existing models like the Information Visualization Reference Model describe the data-to-visual mapping process, they often overlook a crucial intermediary step: design-specific transformations. This process, occurring after data transformation but before visual-data mapping, further derives data, such as groupings, layout, and statistics, that are essential to properly render the visualization. In this paper, we advocate for a deeper exploration of design-specific transformations, highlighting their importance in understanding visualization properties, particularly in relation to user tasks. We incorporate design-specific transformations into the Information Visualization Reference Model and propose a new formalism that encompasses the user task as a function over data. The resulting formalism offers three key benefits over existing visualization models: (1) describing task as compositions of functions, (2) enabling analysis of data transformations for visual-data mapping, and (3) empowering reasoning about visualization correctness and effectiveness. We further discuss the potential implications of this model on visualization theory and visualization experiment design.
Eugene Wu, Yiru Chen, Haneen Mohammed, Zezhou Huang
Human-data interaction (HDI) presents fundamentally different challenges from traditional data management. HDI systems must meet latency, correctness, and consistency needs that stem from usability rather than query semantics; failing to meet these expectations breaks the user experience. Moreover, interfaces and systems are tightly coupled; neither can easily be optimized in isolation, and effective solutions demand their co-design. This dependence also presents a research opportunity: rather than adapt systems to interface demands, systems innovations and database theory can also inspire new interaction and visualization designs. We survey a decade of our lab's work that embraces this coupling and argue that HDI systems are the foundation for reliable, interactive, AI-driven applications.
Fotis Psallidas, Eugene Wu
We highlight the connections between data provenance and interactive visualizations. To do so, we first incrementally add interactions to a visualization and show how these interactions are readily expressible in terms of provenance. We then describe how an interactive visualization system that natively supports provenance can be easily extended with novel interactions.
Eugene Wu
Comparison is a core task in visual analysis. Although there are numerous guidelines to help users design effective visualizations to aid known comparison tasks, there are few formalisms that define the semantics of comparison operations in a way that can serve as the basis for a grammar of comparison interactions. Recent work proposed a formalism called View Composition Algebra (VCA) that enables ad hoc comparisons between any combination of marks, trends, or charts in a visualization interface. However, VCA limits comparisons to visual representations of data that have an identical schema, or where the schemas form a strict subset relationship (e.g., comparing price per state with price, but not with price per county). In contrast, the majority of real-world data - temporal, geographical, organizational - are hierarchical. To bridge this gap, this paper presents an extension to VCA (called VCAH) that enables ad hoc comparisons between visualizations of hierarchical data. VCAH leverages known hierarchical relationships to enable ad hoc comparison of data at different hierarchical granularities. We illustrate applications to hierarchical and Tableau visualizations.
Adam Marcus, Eugene Wu, David Karger, Samuel Madden, Robert Miller
Crowdsourcing markets like Amazon's Mechanical Turk (MTurk) make it possible to task people with small jobs, such as labeling images or looking up phone numbers, via a programmatic interface. MTurk tasks for processing datasets with humans are currently designed with significant reimplementation of common workflows and ad-hoc selection of parameters such as price to pay per task. We describe how we have integrated crowds into a declarative workflow engine called Qurk to reduce the burden on workflow designers. In this paper, we focus on how to use humans to compare items for sorting and joining data, two of the most common operations in DBMSs. We describe our basic query interface and the user interface of the tasks we post to MTurk. We also propose a number of optimizations, including task batching, replacing pairwise comparisons with numerical ratings, and pre-filtering tables before joining them, which dramatically reduce the overall cost of running sorts and joins on the crowd. In an experiment joining two sets of images, we reduce the overall cost from $67 in a naive implementation to about $3, without substantially affecting accuracy or latency. In an end-to-end experiment, we reduced cost by a factor of 14.5.
Leilani Battle, Edward Benson, Aditya Parameswaran, Eugene Wu
Predictive models are often used for real-time decision making. However, typical machine learning techniques ignore feature evaluation cost, and focus solely on the accuracy of the machine learning models obtained utilizing all the features available. We develop algorithms and indexes to support cost-sensitive prediction, i.e., making decisions using machine learning models taking feature evaluation cost into account. Given an item and a online computation cost (i.e., time) budget, we present two approaches to return an appropriately chosen machine learning model that will run within the specified time on the given item. The first approach returns the optimal machine learning model, i.e., one with the highest accuracy, that runs within the specified time, but requires significant up-front precomputation time. The second approach returns a possibly sub- optimal machine learning model, but requires little up-front precomputation time. We study these two algorithms in detail and characterize the scenarios (using real and synthetic data) in which each performs well. Unlike prior work that focuses on a narrow domain or a specific algorithm, our techniques are very general: they apply to any cost-sensitive prediction scenario on any machine learning algorithm.
Fotis Psallidas, Eugene Wu
Data lineage describes the relationship between individual input and output data items of a workflow, and has served as an integral ingredient for both traditional (e.g., debugging, auditing, data integration, and security) and emergent (e.g., interactive visualizations, iterative analytics, explanations, and cleaning) applications. The core, long-standing problem that lineage systems need to address---and the main focus of this paper---is to capture the relationships between input and output data items across a workflow with the goal to streamline queries over lineage. Unfortunately, current lineage systems either incur high lineage capture overheads, or lineage query processing costs, or both. As a result, applications, that in principle can express their logic declaratively in lineage terms, resort to hand-tuned implementations. To this end, we introduce Smoke, an in-memory database engine that neither lineage capture overhead nor lineage query processing needs to be compromised. To do so, Smoke introduces tight integration of the lineage capture logic into physical database operators; efficient, write-optimized lineage representations for storage; and optimizations when future lineage queries are known up-front. Our experiments on microbenchmarks and realistic workloads show that Smoke reduces the lineage capture overhead and streamlines lineage queries by multiple orders of magnitude compared to state-of-the-art alternatives. Our experiments on real-world applications highlight that Smoke can meet the latency requirements of interactive visualizations (e.g., <150ms) and outperform hand-written implementations of data profiling primitives.
Eugene Wu
We draw a connection between data modeling and visualization, namely that a visualization specification defines a mapping from database constraints to visual representations of those constraints. Using this formalism, we show how many visualization design decisions are, in fact, data modeling choices and extend data visualization from single-dataset visualizations to database visualization
Eugene Wu, Raul Castro Fernandez
Panel proposal for an open forum to discuss and debate the future of database research in the context of industry, other research communities, and AI. Includes summaries of past panels, positions from panelists, as well as positions from a sample of the data management community.
Weiyuan Wu, Lampros Flokas, Eugene Wu, Jiannan Wang
As the need for machine learning (ML) increases rapidly across all industry sectors, there is a significant interest among commercial database providers to support "Query 2.0", which integrates model inference into SQL queries. Debugging Query 2.0 is very challenging since an unexpected query result may be caused by the bugs in training data (e.g., wrong labels, corrupted features). In response, we propose Rain, a complaint-driven training data debugging system. Rain allows users to specify complaints over the query's intermediate or final output, and aims to return a minimum set of training examples so that if they were removed, the complaints would be resolved. To the best of our knowledge, we are the first to study this problem. A naive solution requires retraining an exponential number of ML models. We propose two novel heuristic approaches based on influence functions which both require linear retraining steps. We provide an in-depth analytical and empirical analysis of the two approaches and conduct extensive experiments to evaluate their effectiveness using four real-world datasets. Results show that Rain achieves the highest recall@k among all the baselines while still returns results interactively.