Christopher De Sa

Incremental knowledge base construction using DeepDive

Populating a database with unstructured information is a long-standing problem in industry and research that encompasses problems of extraction, cleaning, and integration. Recent names used for this problem include dealing with dark data and knowledge base construction (KBC). In this work, we describe DeepDive, a system that combines database and machine learning ideas to help develop KBC systems, and we present techniques to make the KBC process more efficient. We observe that the KBC process is iterative, and we develop techniques to incrementally produce inference results for KBC systems. We propose two methods for incremental inference, based respectively on sampling and variational techniques. We also study the tradeoff space of these methods and develop a simple rule-based optimizer. DeepDive includes all of these contributions, and we evaluate Deep-Dive on five KBC systems, showing that it can speed up KBC inference tasks by up to two orders of magnitude with negligible impact on quality.

DeepDive: Declarative Knowledge Base Construction

The dark data extraction or knowledge base construction (KBC) problem is to populate a SQL database with information from unstructured data sources including emails, webpages, and pdf reports. KBC is a long-standing problem in industry and research that encompasses problems of data extraction, cleaning, and integration. We describe DeepDive, a system that combines database and machine learning ideas to help develop KBC systems. The key idea in DeepDive is that statistical inference and machine learning are key tools to attack classical data problems in extraction, cleaning, and integration in a unified and more effective manner. DeepDive programs are declarative in that one cannot write probabilistic inference algorithms; instead, one interacts by defining features or rules about the domain. A key reason for this design choice is to enable domain experts to build their own KBC systems. We present the applications, abstractions, and techniques of DeepDive employed to accelerate construction of KBC systems.

Have abstraction and eat performance, too: optimized heterogeneous computing with parallel patterns

High performance in modern computing platforms requires programs to be parallel, distributed, and run on heterogeneous hardware. However programming such architectures is extremely difficult due to the need to implement the application using multiple programming models and combine them together in ad-hoc ways. To optimize distributed applications both for modern hardware and for modern programmers we need a programming model that is sufficiently expressive to support a variety of parallel applications, sufficiently performant to surpass hand-optimized sequential implementations, and sufficiently portable to support a variety of heterogeneous hardware. Unfortunately existing systems tend to fall short of these requirements. In this paper we introduce the Distributed Multiloop Language (DMLL), a new intermediate language based on common parallel patterns that captures the necessary semantic knowledge to efficiently target distributed heterogeneous architectures. We show straightforward analyses that determine what data to distribute based on its usage as well as powerful transformations of nested patterns that restructure computation to enable distribution and optimize for heterogeneous devices. We present experimental results for a range of applications spanning multiple domains and demonstrate highly efficient execution compared to manually-optimized counterparts in multiple distributed programming models.

Generating Configurable Hardware from Parallel Patterns

In recent years the computing landscape has seen an increasing shift towards specialized accelerators. Field programmable gate arrays (FPGAs) are particularly promising for the implementation of these accelerators, as they offer significant performance and energy improvements over CPUs for a wide class of applications and are far more flexible than fixed-function ASICs. However, FPGAs are difficult to program. Traditional programming models for reconfigurable logic use low-level hardware description languages like Verilog and VHDL, which have none of the productivity features of modern software languages but produce very efficient designs, and low-level software languages like C and OpenCL coupled with high-level synthesis (HLS) tools that typically produce designs that are far less efficient. Functional languages with parallel patterns are a better fit for hardware generation because they provide high-level abstractions to programmers with little experience in hardware design and avoid many of the problems faced when generating hardware from imperative languages. In this paper, we identify two important optimizations for using parallel patterns to generate efficient hardware: tiling and metapipelining. We present a general representation of tiled parallel patterns, and provide rules for automatically tiling patterns and generating metapipelines. We demonstrate experimentally that these optimizations result in speedups up to 39.4× on a set of benchmarks from the data analytics domain.

Understanding and Optimizing Asynchronous Low-Precision Stochastic Gradient Descent

Stochastic gradient descent (SGD) is one of the most popular numerical algorithms used in machine learning and other domains. Since this is likely to continue for the foreseeable future, it is important to study techniques that can make it run fast on parallel hardware. In this paper, we provide the first analysis of a technique called BUCKWILD! that uses both asynchronous execution and low-precision computation. We introduce the DMGC model, the first conceptualization of the parameter space that exists when implementing low-precision SGD, and show that it provides a way to both classify these algorithms and model their performance. We leverage this insight to propose and analyze techniques to improve the speed of low-precision SGD. First, we propose software optimizations that can increase throughput on existing CPUs by up to 11×. Second, we propose architectural changes, including a new cache technique we call an obstinate cache, that increase throughput beyond the limits of current-generation hardware. We also implement and analyze low-precision SGD on the FPGA, which is a promising alternative to the CPU for future SGD systems.

DeepDive: declarative knowledge base construction

The dark data extraction or knowledge base construction (KBC) problem is to populate a relational database with information from unstructured data sources, such as emails, webpages, and PDFs. KBC is a long-standing problem in industry and research that encompasses problems of data extraction, cleaning, and integration. We describe DeepDive, a system that combines database and machine learning ideas to help to develop KBC systems. The key idea in DeepDive is to frame traditional extract-transform-load (ETL) style data management problems as a single large statistical inference task that is declaratively defined by the user. DeepDive leverages the effectiveness and efficiency of statistical inference and machine learning for difficult extraction tasks, whereas not requiring users to directly write any probabilistic inference algorithms. Instead, domain experts interact with DeepDive by defining features or rules about the domain. DeepDive has been successfully applied to domains such as pharmacogenomics, paleobiology, and antihuman trafficking enforcement, achieving human-caliber quality at machine-caliber scale. We present the applications, abstractions, and techniques used in DeepDive to accelerate the construction of such dark data extraction systems.

Flipper: A Systematic Approach to Debugging Training Sets

As machine learning methods gain popularity across different fields, acquiring labeled training datasets has become the primary bottleneck in the machine learning pipeline. Recently generative models have been used to create and label large amounts of training data, albeit noisily. The output of these generative models is then used to train a discriminative model of choice, such as logistic regression or a complex neural network. However, any errors in the generative model can propagate to the subsequent model being trained. Unfortunately, these generative models are not easily interpretable and are therefore difficult to debug for users. To address this, we present our vision for Flipper, a framework that presents users with high-level information about why their training set is inaccurate and informs their decisions as they improve their generative model manually. We present potential tools within the Flipper framework, inspired by observing biomedical experts working with generative models, which allow users to analyze the errors in their training data in a systematic fashion. Finally, we discuss a prototype of Flipper and report results of a user study where users create a training set for a classification task and improve the discriminative models accuracy by 2.4 points in less than an hour with feedback from Flipper.

Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling.

Gibbs sampling is a Markov chain Monte Carlo technique commonly used for estimating marginal distributions. To speed up Gibbs sampling, there has recently been interest in parallelizing it by executing asynchronously. While empirical results suggest that many models can be efficiently sampled asynchronously, traditional Markov chain analysis does not apply to the asynchronous case, and thus asynchronous Gibbs sampling is poorly understood. In this paper, we derive a better understanding of the two main challenges of asynchronous Gibbs: bias and mixing time. We show experimentally that our theoretical results match practical outcomes.