arXiv subjects

Juliana Freire

Publications and source records attributed to Juliana Freire.

At least 55 records · Page 3Linked to original sources

arXiv2020

A GPU-friendly Geometric Data Model and Algebra for Spatial Queries: Extended Version

The availability of low cost sensors has led to an unprecedented growth in the volume of spatial data. However, the time required to evaluate even simple spatial queries over large data sets greatly hampers our ability to interactively explore these data sets and extract actionable insights. Graphics Processing Units~(GPUs) are increasingly being used to speedup spatial queries. However, existing GPU-based solutions have two important drawbacks: they are often tightly coupled to the specific query types they target, making it hard to adapt them for other queries; and since their design is based on CPU-based approaches, it can be difficult to effectively utilize all the benefits provided by the GPU. As a first step towards making GPU spatial query processing mainstream, we propose a new model that represents spatial data as geometric objects and define an algebra consisting of GPU-friendly composable operators that operate over these objects. We demonstrate the expressiveness of the proposed algebra by formulating standard spatial queries as algebraic expressions. We also present a proof-of-concept prototype that supports a subset of the operators and show that it is at least two orders of magnitude faster than a CPU-based implementation. This performance gain is obtained both using a discrete Nvidia mobile GPU and the less powerful integrated GPUs common in commodity laptops.

cs.DB↗

arXiv2020

Debugging Machine Learning Pipelines

Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pipeline produce erroneous or uninformative outputs, the pipeline may fail or produce incorrect results. Inferring the root cause of failures and unexpected behavior is challenging, usually requiring much human thought, and is both time-consuming and error-prone. We propose a new approach that makes use of iteration and provenance to automatically infer the root causes and derive succinct explanations of failures. Through a detailed experimental evaluation, we assess the cost, precision, and recall of our approach compared to the state of the art. Our source code and experimental data will be available for reproducibility and enhancement.

cs.LG↗

arXiv2019

AutoML using Metadata Language Embeddings

As a human choosing a supervised learning algorithm, it is natural to begin by reading a text description of the dataset and documentation for the algorithms you might use. We demonstrate that the same idea improves the performance of automated machine learning methods. We use language embeddings from modern NLP to improve state-of-the-art AutoML systems by augmenting their recommendations with vector embeddings of datasets and of algorithms. We use these embeddings in a neural architecture to learn the distance between best-performing pipelines. The resulting (meta-)AutoML framework improves on the performance of existing AutoML frameworks. Our zero-shot AutoML system using dataset metadata embeddings provides good solutions instantaneously, running in under one second of computation. Performance is competitive with AutoML systems OBOE, AutoSklearn, AlphaD3M, and TPOT when each framework is allocated a minute of computation. We make our data, models, and code publicly available.

cs.LG↗

arXiv2019

Visus: An Interactive System for Automatic Machine Learning Model Building and Curation

While the demand for machine learning (ML) applications is booming, there is a scarcity of data scientists capable of building such models. Automatic machine learning (AutoML) approaches have been proposed that help with this problem by synthesizing end-to-end ML data processing pipelines. However, these follow a best-effort approach and a user in the loop is necessary to curate and refine the derived pipelines. Since domain experts often have little or no expertise in machine learning, easy-to-use interactive interfaces that guide them throughout the model building process are necessary. In this paper, we present Visus, a system designed to support the model building process and curation of ML data processing pipelines generated by AutoML systems. We describe the framework used to ground our design choices and a usage scenario enabled by Visus. Finally, we discuss the feedback received in user testing sessions with domain experts.

cs.LG↗

arXiv2019

Automatic Machine Learning by Pipeline Synthesis using Model-Based Reinforcement Learning and a Grammar

Automatic machine learning is an important problem in the forefront of machine learning. The strongest AutoML systems are based on neural networks, evolutionary algorithms, and Bayesian optimization. Recently AlphaD3M reached state-of-the-art results with an order of magnitude speedup using reinforcement learning with self-play. In this work we extend AlphaD3M by using a pipeline grammar and a pre-trained model which generalizes from many different datasets and similar tasks. Our results demonstrate improved performance compared with our earlier work and existing methods on AutoML benchmark datasets for classification and regression tasks. In the spirit of reproducible research we make our data, models, and code publicly available.

cs.LG↗

arXiv2019

A Topic-Agnostic Approach for Identifying Fake News Pages

Fake news and misinformation have been increasingly used to manipulate popular opinion and influence political processes. To better understand fake news, how they are propagated, and how to counter their effect, it is necessary to first identify them. Recently, approaches have been proposed to automatically classify articles as fake based on their content. An important challenge for these approaches comes from the dynamic nature of news: as new political events are covered, topics and discourse constantly change and thus, a classifier trained using content from articles published at a given time is likely to become ineffective in the future. To address this challenge, we propose a topic-agnostic (TAG) classification strategy that uses linguistic and web-markup features to identify fake news pages. We report experimental results using multiple data sets which show that our approach attains high accuracy in the identification of fake news, even as topics evolve over time.

cs.CL↗

arXiv2019

Bootstrapping Domain-Specific Content Discovery on the Web

The ability to continuously discover domain-specific content from the Web is critical for many applications. While focused crawling strategies have been shown to be effective for discovery, configuring a focused crawler is difficult and time-consuming. Given a domain of interest $D$, subject-matter experts (SMEs) must search for relevant websites and collect a set of representative Web pages to serve as training examples for creating a classifier that recognizes pages in $D$, as well as a set of pages to seed the crawl. In this paper, we propose DISCO, an approach designed to bootstrap domain-specific search. Given a small set of websites, DISCO aims to discover a large collection of relevant websites. DISCO uses a ranking-based framework that mimics the way users search for information on the Web: it iteratively discovers new pages, distills, and ranks them. It also applies multiple discovery strategies, including keyword-based and related queries issued to search engines, backward and forward crawling. By systematically combining these strategies, DISCO is able to attain high harvest rates and coverage for a variety of domains. We perform extensive experiments in four social-good domains, using data gathered by SMEs in the respective domains, and show that our approach is effective and outperforms state-of-the-art methods.

cs.IR↗

arXiv2018

ReproServer: Making Reproducibility Easier and Less Intensive

Reproducibility in the computational sciences has been stymied because of the complex and rapidly changing computational environments in which modern research takes place. While many will espouse reproducibility as a value, the challenge of making it happen (both for themselves and testing the reproducibility of others' work) often outweigh the benefits. There have been a few reproducibility solutions designed and implemented by the community. In particular, the authors are contributors to ReproZip, a tool to enable computational reproducibility by tracing and bundling together research in the environment in which it takes place (e.g. one's computer or server). In this white paper, we introduce a tool for unpacking ReproZip bundles in the cloud, ReproServer. ReproServer takes an uploaded ReproZip bundle (.rpz file) or a link to a ReproZip bundle, and users can then unpack them in the cloud via their browser, allowing them to reproduce colleagues' work without having to install anything locally. This will help lower the barrier to reproducing others' work, which will aid reviewers in verifying the claims made in papers and reusing previously published research.

cs.SE↗

arXiv2017

A Collaborative Approach to Computational Reproducibility

Although a standard in natural science, reproducibility has been only episodically applied in experimental computer science. Scientific papers often present a large number of tables, plots and pictures that summarize the obtained results, but then loosely describe the steps taken to derive them. Not only can the methods and the implementation be complex, but also their configuration may require setting many parameters and/or depend on particular system configurations. While many researchers recognize the importance of reproducibility, the challenge of making it happen often outweigh the benefits. Fortunately, a plethora of reproducibility solutions have been recently designed and implemented by the community. In particular, packaging tools (e.g., ReproZip) and virtualization tools (e.g., Docker) are promising solutions towards facilitating reproducibility for both authors and reviewers. To address the incentive problem, we have implemented a new publication model for the Reproducibility Section of Information Systems Journal. In this section, authors submit a reproducibility paper that explains in detail the computational assets from a previous published manuscript in Information Systems.

cs.DL↗

arXiv2016

Data Polygamy: The Many-Many Relationships among Urban Spatio-Temporal Data Sets

The increasing ability to collect data from urban environments, coupled with a push towards openness by governments, has resulted in the availability of numerous spatio-temporal data sets covering diverse aspects of a city. Discovering relationships between these data sets can produce new insights by enabling domain experts to not only test but also generate hypotheses. However, discovering these relationships is difficult. First, a relationship between two data sets may occur only at certain locations and/or time periods. Second, the sheer number and size of the data sets, coupled with the diverse spatial and temporal scales at which the data is available, presents computational challenges on all fronts, from indexing and querying to analyzing them. Finally, it is non-trivial to differentiate between meaningful and spurious relationships. To address these challenges, we propose Data Polygamy, a scalable topology-based framework that allows users to query for statistically significant relationships between spatio-temporal data sets. We have performed an experimental evaluation using over 300 spatial-temporal urban data sets which shows that our approach is scalable and effective at identifying interesting relationships.

cs.DB↗

arXiv2016

The Exception that Improves the Rule

The database community has developed numerous tools and techniques for data curation and exploration, from declarative languages, to specialized techniques for data repair, and more. Yet, there is currently no consensus on how to best expose these powerful tools to an analyst in a simple, intuitive, and above all, flexible way. Thus, analysts continue to rely on tools such as spreadsheets, imperative languages, and notebook style programming environments like Jupyter for data curation. In this work, we explore the integration of spreadsheets, notebooks, and relational databases. We focus on a key advantage that both spreadsheets and imperative notebook environments have over classical relational databases: ease of exception. By relying on set-at-a-time operations, relational databases sacrifice the ability to easily define singleton operations, exceptions to a normal data processing workflow that affect query processing for a fixed set of explicitly targeted records. In comparison, a spreadsheet user can easily change the formula for just one cell, while a notebook user can add an imperative operation to her notebook that alters an output 'view'. We believe that enabling such idiosyncratic manual transformations in a classical relational database is critical for curation, as curation operations that are easy to declare for individual values can often be extremely challenging to generalize. We explore the challenges of enabling singletons in relational databases, propose a hybrid spreadsheet/relational notebook environment for data curation, and present our vision of Vizier, a system that exposes data curation through such an interface.

cs.DB↗

arXiv2016

RioBusData: Outlier Detection in Bus Routes of Rio de Janeiro

Buses are the primary means of public transportation in the city of Rio de Janeiro, carrying around 100 million passengers every month. Recently, real-time GPS coordinates of all operating public buses has been made publicly available - roughly 1 million GPS entries each captured each day. In an initial study, we observed that a substantial number of buses follow trajectories that do not follow the expected behavior. In this paper, we present RioBusData, a tool that helps users identify and explore, through different visualizations, the behavior of outlier trajectories. We describe how the system automatically detects these outliers using a Convolutional Neural Network (CNN) and we also discuss a series of case studies which show how RioBusData helps users better understand not only the flow and service of outlier buses but also the bus system as a whole.

cs.HC↗

arXiv2016

Scaling limits of discrete copulas are bridged Brownian sheets

For large $n$, take a random $n \times n$ permutation matrix and its associated discrete copula $X_n$. For $a, b = 0, 1, \ldots, n$, let $y_n(\frac{a}{n},\frac{b}{n}) = \frac{1}{n} ( X_{a,b} - \frac{ab}{n} )$; define $y_n: [0,1]^2 \to R$ by interpolating quadratically on squares of side $\frac{1}{n}$. We prove a Donsker type central limit theorem: $\sqrt{n} y_n$ approaches a bridged Brownian sheet on the unit square.

math.PR↗

arXiv2015

YesWorkflow: A User-Oriented, Language-Independent Tool for Recovering Workflow Information from Scripts

Scientific workflow management systems offer features for composing complex computational pipelines from modular building blocks, for executing the resulting automated workflows, and for recording the provenance of data products resulting from workflow runs. Despite the advantages such features provide, many automated workflows continue to be implemented and executed outside of scientific workflow systems due to the convenience and familiarity of scripting languages (such as Perl, Python, R, and MATLAB), and to the high productivity many scientists experience when using these languages. YesWorkflow is a set of software tools that aim to provide such users of scripting languages with many of the benefits of scientific workflow systems. YesWorkflow requires neither the use of a workflow engine nor the overhead of adapting code to run effectively in such a system. Instead, YesWorkflow enables scientists to annotate existing scripts with special comments that reveal the computational modules and dataflows otherwise implicit in these scripts. YesWorkflow tools extract and analyze these comments, represent the scripts in terms of entities based on the typical scientific workflow model, and provide graphical renderings of this workflow-like view of the scripts. Future versions of YesWorkflow also will allow the prospective provenance of the data products of these scripts to be queried in ways similar to those available to users of scientific workflow systems.

cs.SE↗

arXiv2015

Maximum Common Subelement Metrics and its Applications to Graphs

In this paper we characterize a mathematical model called Maximum Common Subelement (MCS) Model and prove the existence of four different metrics on such model. We generalize metrics on graphs previously proposed in the literature and identify new ones by showing three different examples of MCS Models on graphs based on (1) subgraphs, (2) induced subgraphs and (3) an extended notion of subgraphs. This latter example can be used to model graphs with complex labels (e.g., graphs whose labels are other graphs), and hence to derive metrics on them. Furthermore, we also use (3) to show that graph edit distance, when a metric, is related to a maximum common subelement in a corresponding MCS Model.

cs.DM↗

arXiv2013

Enabling Reproducible Science with VisTrails

With the increasing amount of data and use of computation in science, software has become an important component in many different domains. Computing is now being used more often and in more aspects of scientific work including data acquisition, simulation, analysis, and visualization. To ensure reproducibility, it is important to capture the different computational processes used as well as their executions. VisTrails is an open-source scientific workflow system for data analysis and visualization that seeks to address the problem of integrating varied tools as well as automatically documenting the methods and parameters employed. Growing from a specific project need to supporting a wide array of users required close collaborations in addition to new research ideas to design a usable and efficient system. The VisTrails project now includes standard software processes like unit testing and developer documentation while serving as a base for further research. In this paper, we describe how VisTrails has developed and how our efforts in structuring and advertising the system have contributed to its adoption in many domains.

cs.SE↗

arXiv2011

Multilingual Schema Matching for Wikipedia Infoboxes

Recent research has taken advantage of Wikipedia's multilingualism as a resource for cross-language information retrieval and machine translation, as well as proposed techniques for enriching its cross-language structure. The availability of documents in multiple languages also opens up new opportunities for querying structured Wikipedia content, and in particular, to enable answers that straddle different languages. As a step towards supporting such queries, in this paper, we propose a method for identifying mappings between attributes from infoboxes that come from pages in different languages. Our approach finds mappings in a completely automated fashion. Because it does not require training data, it is scalable: not only can it be used to find mappings between many language pairs, but it is also effective for languages that are under-represented and lack sufficient training samples. Another important benefit of our approach is that it does not depend on syntactic similarity between attribute names, and thus, it can be applied to language pairs that have distinct morphologies. We have performed an extensive experimental evaluation using a corpus consisting of pages in Portuguese, Vietnamese, and English. The results show that not only does our approach obtain high precision and recall, but it also outperforms state-of-the-art techniques. We also present a case study which demonstrates that the multilingual mappings we derive lead to substantial improvements in answer quality and coverage for structured queries over Wikipedia content.

cs.DB↗

arXiv2011

Synthesizing Products for Online Catalogs

A high-quality, comprehensive product catalog is essential to the success of Product Search engines and shopping sites such as Yahoo! Shopping, Google Product Search or Bing Shopping. But keeping catalogs up-to-date becomes a challenging task, calling for the need of automated techniques. In this paper, we introduce the problem of product synthesis, a key component of catalog creation and maintenance. Given a set of offers advertised by merchants, the goal is to identify new products and add them to the catalog together with their (structured) attributes. A fundamental challenge is the scale of the problem: a Product Search engine receives data from thousands of merchants and millions of products; the product taxonomy contains thousands of categories, where each category comes in a different schema; and merchants use representations for products that are different from the ones used in the catalog of the Product Search engine. We propose a system that provides an end-to-end solution to the product synthesis problem, and includes components for extraction, and addresses issues involved in data extraction from offers, schema reconciliation, and data fusion. We developed a novel and scalable technique for schema matching which leverages knowledge about previously-known instance-level associations between offers and products; and it is trained using automatically created training sets (no manually-labeled data is needed). We present an experimental evaluation of our system using data from Bing Shopping for more than 800K offers, a thousand merchants, and 400 categories. The evaluation confirms that our approach is able to automatically generate a large number of accurate product specifications, and that our schema reconciliation component outperforms state-of-the-art schema matching techniques in terms of precision and recall.

cs.DB↗