Search NASA⌕ Search

Engineering topics

Liu, Shusen

Publications and source records attributed to Liu, Shusen.

At least 19 records

A Visual Comparison of Silent Error Propagation

High-performance computing (HPC) systems play a critical role in facilitating scientific discoveries. Their scale and complexity (e.g., the number of computational units and software stack) continue to grow as new systems are expected to process increasingly more data and reduce computing time. However, with more processing elements, the probability that these systems will experience a random bit-flip error that corrupts a program's output also increases, which is often recognized as silent data corruption. Analyzing the resiliency of HPC applications in extreme-scale computing to silent data corruption is crucial but difficult. An HPC application often contains a large number of computation units that need to be tested, and error propagation caused by error corruption is complex and difficult to interpret. Here, to accommodate this challenge, we propose an interactive visualization system that helps HPC researchers understand the resiliency of HPC applications and compare their error propagation. Our system models an application's error propagation to study a program's resiliency by constructing and visualizing its fault tolerance boundary. Coordinating with multiple interactive designs, our system enables domain experts to efficiently explore the complicated spatial and temporal correlation between error propagations. At the end, the system integrated a nonmonotonic error propagation analysis with an adjustable graph propagation visualization to help domain experts examine the details of error propagation and answer such questions as why an error is mitigated or amplified by program execution.

97 MATHEMATICS AND COMPUTING↗

Generative attribute optimization

A generative attribute optimization (“GAO”) system facilitates understanding of effects of changes of attribute values of an object on a characteristic of the object and automatically identifying attribute values to achieve a desired result for the characteristic. The GAO system trains a generator (encoder and decoder) using an attribute generative adversarial network. The GAO model includes the trained generator and a separately trained predictor model. The GAO model inputs an input image and modified attribute values and employs the encoder and the decoder to generate a modified image that is the input image modified based on the modified attribute values. The GAO model then employs the predictor model to that inputs the modified image and generate a prediction of a characteristic of the modified image. The GAO system may employ an optimizer to modify the attribute values until an objective based on the desired result is achieved.

97 MATHEMATICS AND COMPUTING↗

Interactively Assessing Disentanglement in GANs

Abstract Generative adversarial networks (GAN) have witnessed tremendous growth in recent years, demonstrating wide applicability in many domains. However, GANs remain notoriously difficult for people to interpret, particularly for modern GANs capable of generating photo‐realistic imagery. In this work we contribute a visual analytics approach for GAN interpretability, where we focus on the analysis and visualization of GAN disentanglement. Disentanglement is concerned with the ability to control content produced by a GAN along a small number of distinct, yet semantic, factors of variation. The goal of our approach is to shed insight on GAN disentanglement, above and beyond coarse summaries, instead permitting a deeper analysis of the data distribution modeled by a GAN. Our visualization allows one to assess a single factor of variation in terms of groupings and trends in the data distribution, where our analysis seeks to relate the learned representation space of GANs with attribute‐based semantic scoring of images produced by GANs. Through use‐cases, we show that our visualization is effective in assessing disentanglement, allowing one to quickly recognize a factor of variation and its overall quality. In addition, we show how our approach can highlight potential dataset biases learned by GANs.

Jeong, Sangwon↗

Machine learning–driven multiscale modeling reveals lipid-dependent dynamics of RAS signaling proteins

Significance Here we present an unprecedented multiscale simulation platform that enables modeling, hypothesis generation, and discovery across biologically relevant length and time scales to predict mechanisms that can be tested experimentally. We demonstrate that our predictive simulation-experimental validation loop generates accurate insights into RAS-membrane biology. Evaluating over 100,000 correlated simulations, we show that RAS–lipid interactions are dynamic and evolving, resulting in: 1) a reordering and selection of lipid domains in realistic eight-lipid bilayers, 2) clustering of RAS into multimers correlating with specific lipid fingerprints, 3) changes in the orientation of the RAS G-domain impacting its ability to interact with effectors, and 4) demonstration that RAS–RAS G-domain interfaces are nonspecific in these putative signaling domains.

59 BASIC BIOLOGICAL SCIENCES↗

Machine-learning-based dynamic-importance sampling for adaptive multiscale simulations

Multiscale simulations are a well-accepted way to bridge the length and time scales required for scientific studies with the solution accuracy achievable through available computational resources. Traditional approaches either solve a coarse model with selective refinement or coerce a detailed model into faster sampling, both of which have limitations. Here, we present a paradigm of adaptive, multiscale simulations that couple different scales using a dynamic-importance sampling approach. Our method uses machine learning to dynamically and exhaustively sample the phase space explored by a macro model using microscale simulations and enables an automatic feedback from the micro to the macro scale, leading to a self-healing multiscale simulation. As a result, our approach delivers macro length and time scales, but with the effective precision of the micro scale. Our approach is arbitrarily scalable as well as transferable to many different types of simulations. Overall, our method made possible a multiscale scientific campaign of unprecedented scale to understand the interactions of RAS proteins with a plasma membrane in the context of cancer research running over several days on Sierra, which is currently the second-most-powerful supercomputer in the world.

59 BASIC BIOLOGICAL SCIENCES↗

SpotSDC: Revealing the Silent Data Corruption Propagation in High-Performance Computing Systems

We report the trend of rapid technology scaling is expected to make the hardware of high-performance computing (HPC) systems more susceptible to computational errors due to random bit flips. Some bit flips may cause a program to crash or have a minimal effect on the output, but others may lead to silent data corruption (SDC), i.e., undetected yet significant output errors. Classical fault injection analysis methods employ uniform sampling of random bit flips during program execution to derive a statistical resiliency profile. However, summarizing such fault injection result with sufficient detail is difficult, and understanding the behavior of the fault-corrupted program is still a challenge. In this article, we introduce SpotSDC, a visualization system to facilitate the analysis of a program's resilience to SDC. SpotSDC provides multiple perspectives at various levels of detail of the impact on the output relative to where in the source code the flipped bit occurs, which bit is flipped, and when during the execution it happens. SpotSDC also enables users to study the code protection and provide new insights to understand the behavior of a fault-injected program. Based on lessons learned, we demonstrate how what we found can improve the fault injection campaign method.

97 MATHEMATICS AND COMPUTING↗

Nanomaterial Synthesis Insights from Machine Learning of Scientific Articles by Extracting, Structuring, and Visualizing Knowledge

Nanomaterials of varying compositions and morphologies are of interest for many applications from catalysis to optics, but the synthesis of nanomaterials and their scale-up are most often time-consuming and Edisonian processes. Information gleaned from the scientific literature can help inform and accelerate nanomaterials development, but again, searching the literature and digesting the information are time-consuming manual processes for researchers. To help address these challenges, here we developed scientific article-processing tools that extract and structure information from the text and figures of nanomaterials articles, thereby enabling the creation of a personalized knowledgebase for nanomaterials synthesis that can be mined to help inform further nanomaterials development. Starting with a corpus of ~35k nanomaterials-related articles, we developed models to classify articles according to the nanomaterial composition and morphology, extract synthesis protocols from within the articles’ text, and extract, normalize, and categorize chemical terms within synthesis protocols. We demonstrate the efficiency of the proposed pipeline on an expert-labeled set of nanomaterials synthesis articles, achieving 100% accuracy on composition prediction, 95% accuracy on morphology prediction, 0.99 AUC on protocol identification, and up to a 0.87 F1-score on chemical entity recognition. In addition to processing articles’ text, microscopy images of nanomaterials within the articles are also automatically identified and analyzed to determine the nanomaterials’ morphologies and size distributions. To enable users to easily explore the database, we developed a complementary browser-based visualization tool that provides flexibility in comparing across subsets of articles of interest. We use these tools and information to identify trends in nanomaterials synthesis, such as the correlation of certain reagents with various nanomaterial morphologies, which is useful in guiding hypotheses and reducing the potential parameter space during experimental design.

36 MATERIALS SCIENCE↗

Scalable Topological Data Analysis and Visualization for Evaluating Data-Driven Models in Scientific Applications

With the rapid adoption of machine learning techniques for large-scale applications in science and engineering comes the convergence of two grand challenges in visualization. First, the utilization of black box models (e.g., deep neural networks) calls for advanced techniques in exploring and interpreting model behaviors. Second, the rapid growth in computing has produced enormous datasets that require techniques that can handle millions or more samples. Although some solutions to these interpretability challenges have been proposed, they typically do not scale beyond thousands of samples, nor do they provide the high-level intuition scientists are looking for. Here, we present the first scalable solution to explore and analyze high-dimensional functions often encountered in the scientific data analysis pipeline. By combining a new streaming neighborhood graph construction, the corresponding topology computation, and a novel data aggregation scheme, namely topology aware datacubes, we enable interactive exploration of both the topological and the geometric aspect of high-dimensional data. Following two use cases from high-energy-density (HED) physics and computational biology, we demonstrate how these capabilities have led to crucial new insights in both applications.

97 MATHEMATICS AND COMPUTING↗

Materials Informatics ChemVis

A Browser-based visualization of morphology, material, and chemical data extracted from chemical papers. This UI is focused for specifically nanomaterial synthesis papers. The visual analytic environment allows the user to explore a large number of papers quickly, through an interactive, intuitive, and visual way that helps see possible trends in the data. This exploration-oriented systems allows domain experts who may not have an extensive background in writing analysis code or database queries to easily express their idea to experiment on the data and view the results. The visualization software requires the data in JSON format. The data packaged with the software is the result of 35k nanomaterial synthesis papers queried from Elsevier, created through a separate software pipeline. The data contains information such as the title, authors, chemicals, and created material and morphology.

Liu, Shusen↗

Function Preserving Projection (FPP): A Linear Projection Technique for Visual Interpretation of High-Dimensional Functions

In this work, we propose function preserving projection (FPP), a new class of scalable linear projection techniques for finding interpretable structure in highdimensional datasets. Instead of focusing on preserving the structure of highdimensional points as traditional dimensionality reduction methods, we aim to find a 2D view of the data, in which human interpretable patterns of meaningful properties (that defined on the high-dimensional points, i.e., functions in a highdimensional domain) are revealed. Such a visual-centric approach introduces new avenues for exploratory data analysis and allows efficient implementation that provides a scalable tool for exploring potentially unknown or unexpected relationships in complex and large high-dimensional data (e.g., beyond millions of samples and tens of thousands of dimensions).

97 MATHEMATICS AND COMPUTING↗

Understanding Dynamical Systems in High-Dimensional Parameter Spaces (Final Report)

In the last few decades, computational models, especially of the complex dynamical systems of greatest interest, i.e., climate, high energy density science, combustion, etc. have become increasingly accurate and sophisticated. Consequently, they are now routinely used to predict outcomes of experiments or to inform design decisions. However, many such simulations depend on a (large) number of parameters in order to, for example, approximate physical phenom whose exact solution is unknown or describe material properties in situations with little or no experimental data. Choosing these parameters and understanding how the outcomes of such a simulation changes with respect to the inputs are rapidly becoming some of the primary challenges in many application areas. Simulations have long been too complex for humans to fully comprehend and thus are often treated as black-box systems. The inputs to the systems are typically a collection of parameters with expert-selected ranges, and the outputs are various quantities of interest (QoIs) describing the performance of the system. Therefore, the fundamental challenge can be described as one of understanding a high-dimensional (many input parameters), multi-variate (many QoIs) function. Unfortunately, existing analysis tools are only of limited use for this task as most techniques can neither deal with many input dimensions nor offer opportunities to jointly study several QoIs. Furthermore, data analysis has long relied on an exploratory process in which scientist first visualize the available data, for example, using scatter plots or 3D renderings, form new hypotheses on some phenomena of interest, and subsequently test these hypotheses using dedicated analysis or statistics approaches. However, for high-dimensional functions this exploration is difficult if not impossible using existing tools as there are too many QoIs to simultaneously observe, and visualizations of high-dimensional spaces are abstract and difficult to understand if they exist at all. The goal of this project is to build new analysis techniques and tool that offer high level insights for exploring high-dimensional scientific data. And to extend existing approach beyond single scalar functions and instead consider multiple QoIs simultaneously.

97 MATHEMATICS AND COMPUTING↗

NLIZE: A Perturbation-Driven Visual Interrogation Tool for Analyzing and Interpreting Natural Language Inference Models

With the recent advances in deep learning, neural network models have obtained state-of-the-art performances for many linguistic tasks in natural language processing. However, this rapid progress also brings enormous challenges. The opaque nature of a neural network model leads to hard-to-debug-systems and difficult-to-interpret mechanisms. Here, we introduce a visualization system that, through a tight yet flexible integration between visualization elements and the underlying model, allows a user to interrogate the model by perturbing the input, internal state, and prediction while observing changes in other parts of the pipeline. We use the natural language inference problem to illustrate how a perturbation-driven paradigm can help domain experts assess the potential limitation of a model, probe its inner states, and interpret and form hypotheses about fundamental model mechanisms such as attention.

97 MATHEMATICS AND COMPUTING↗

NLPVis

NLPVis is a visualization system that, through a tight yet flexible integration between visualization elements and the underlying model, allows a user to interrogate the modal by perturbing the input, internal state, and prediction while observing changes.

Liu, Shusen↗

NDDAV

Web-based Interface for the N-Dimensional Data Analysis and Visualization System.

Liu, Shusen↗

Visual Exploration of Semantic Relationships in Neural Word Embeddings

Constructing distributed representations for words through neural language models and using the resulting vector spaces for analysis has become a crucial component of natural language processing (NLP). But, despite their widespread application, little is known about the structure and properties of these spaces. To gain insights into the relationship between words, the NLP community has begun to adapt high-dimensional visualization techniques. Particularly, researchers commonly use t-distributed stochastic neighbor embeddings (t-SNE) and principal component analysis (PCA) to create two-dimensional embeddings for assessing the overall structure and exploring linear relationships (e.g., word analogies), respectively. Unfortunately, these techniques often produce mediocre or even misleading results and cannot address domain-specific visualization challenges that are crucial for understanding semantic relationships in word embeddings. We introduce new embedding techniques for visualizing semantic and syntactic analogies, and the corresponding tests to determine whether the resulting views capture salient structures. Additionally, we introduce two novel views for a comprehensive study of analogy relationships. Finally, we augment t-SNE embeddings to convey uncertainty information in order to allow a reliable interpretation. Combined, the different views address a number of domain-specific tasks difficult to solve with existing tools.

97 MATHEMATICS AND COMPUTING↗

Multivariate volume visualization through dynamic projections

We propose a multivariate volume visualization framework that tightly couples dynamic projections with a high-dimensional transfer function design for interactive volume visualization. We assume that the complex, high-dimensional data in the attribute space can be well-represented through a collection of low-dimensional linear subspaces, and embed the data points in a variety of 2D views created as projections onto these subspaces. Through dynamic projections, we present animated transitions between different views to help the user navigate and explore the attribute space for effective transfer function design. Our framework not only provides a more intuitive understanding of the attribute space but also allows the design of the transfer function under multiple dynamic views, which is more flexible than being restricted to a single static view of the data. For large volumetric datasets, we maintain interactivity during the transfer function design via intelligent sampling and scalable clustering. As a result, using examples in combustion and climate simulations, we demonstrate how our framework can be used to visualize interesting structures in the volumetric space.

97 MATHEMATICS AND COMPUTING↗