arXiv subjects

Junpeng Wang

Publications and source records attributed to Junpeng Wang.

66 records · Page 4Linked to original sources

arXiv2022

3D-TSV: The 3D Trajectory-based Stress Visualizer

We present the 3D Trajectory-based Stress Visualizer (3D-TSV), a visual analysis tool for the exploration of the principal stress directions in 3D solids under load. 3D-TSV provides a modular and generic implementation of key algorithms required for a trajectory-based visual analysis of principal stress directions, including the automatic seeding of space-filling stress lines, their extraction using numerical schemes, their mapping to an effective renderable representation, and rendering options to convey structures with special mechanical properties. In the design of 3D-TSV, several perceptual challenges have been addressed when simultaneously visualizing three mutually orthogonal stress directions via lines. We present a novel algorithm for generating a space-filling and evenly spaced set of mutually orthogonal lines. The algorithm further considers the locations of lines to obtain a more regular appearance, and enables the extraction of a level-of-detail representation with adjustable sparseness of the trajectories along a certain stress direction. To convey ambiguities in the orientation of the principal stress directions, the user can select a combined visualization of two principal directions via oriented ribbons. Additional depth cues improve the perception of the spatial relationships between trajectories. 3D-TSV is accessible to end users via a C++- and OpenGL-based rendering frontend that is seamlessly connected to a MatLab-based extraction backend. The code (BSD license) of 3D-TSV as well as scripts to make ANSYS and ABAQUS simulation results accessible to the 3D-TSV backend are publicly available.

cs.GR↗

arXiv2022

SQRQuerier: A Visual Querying Framework for Cross-national Survey Data Recycling

Public opinion surveys constitute a powerful tool to study peoples' attitudes and behaviors in comparative perspectives. However, even worldwide surveys provide only partial geographic and time coverage, which hinders comprehensive knowledge production. To broaden the scope of comparison, social scientists turn to ex-post harmonization of variables from datasets that cover similar topics but in different populations and/or years. The resulting new datasets can be analyzed as a single source, which can be flexibly accessed through many data portals. However, such portals offer little guidance to explore the data in-depth or query data with user-customized needs. As a result, it is still challenging for social scientists to efficiently identify related data for their studies and evaluate their theoretical models based on the sliced data. To overcome them, in the Survey Data Recycling (SDR) international cooperation research project, we propose SDRQuerier and apply it to the harmonized SDR database, which features over two million respondents interviewed in a total of 1,721 national surveys that are part of 22 well-known international projects. We design the SDRQuerier to solve three practical challenges that social scientists routinely face. First, a BERT-based model provides customized data queries through research questions or keywords. Second, we propose a new visual design to showcase the availability of the harmonized data at different levels, thus helping users decide if empirical data exist to address a given research question. Lastly, SDRQuerier discloses the underlying relational patterns among substantive and methodological variables in the database, to help social scientists rigorously evaluate or even improve their regression models. Through case studies with multiple social scientists in solving their daily challenges, we demonstrated the novelty, effectiveness of SDRQuerier.

cs.HC↗

arXiv2022

Learning-From-Disagreement: A Model Comparison and Visual Analytics Framework

With the fast-growing number of classification models being produced every day, numerous model interpretation and comparison solutions have also been introduced. For example, LIME and SHAP can interpret what input features contribute more to a classifier's output predictions. Different numerical metrics (e.g., accuracy) can be used to easily compare two classifiers. However, few works can interpret the contribution of a data feature to a classifier in comparison with its contribution to another classifier. This comparative interpretation can help to disclose the fundamental difference between two classifiers, select classifiers in different feature conditions, and better ensemble two classifiers. To accomplish it, we propose a learning-from-disagreement (LFD) framework to visually compare two classification models. Specifically, LFD identifies data instances with disagreed predictions from two compared classifiers and trains a discriminator to learn from the disagreed instances. As the two classifiers' training features may not be available, we train the discriminator through a set of meta-features proposed based on certain hypotheses of the classifiers to probe their behaviors. Interpreting the trained discriminator with the SHAP values of different meta-features, we provide actionable insights into the compared classifiers. Also, we introduce multiple metrics to profile the importance of meta-features from different perspectives. With these metrics, one can easily identify meta-features with the most complementary behaviors in two classifiers, and use them to better ensemble the classifiers. We focus on binary classification models in the financial services and advertising industry to demonstrate the efficacy of our proposed framework and visualizations.

cs.LG↗

arXiv2021

Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks

Predicting metrics associated with entities' transnational behavior within payment processing networks is essential for system monitoring. Multivariate time series, aggregated from the past transaction history, can provide valuable insights for such prediction. The general multivariate time series prediction problem has been well studied and applied across several domains, including manufacturing, medical, and entomology. However, new domain-related challenges associated with the data such as concept drift and multi-modality have surfaced in addition to the real-time requirements of handling the payment transaction data at scale. In this work, we study the problem of multivariate time series prediction for estimating transaction metrics associated with entities in the payment transaction database. We propose a model with five unique components to estimate the transaction metrics from multi-modality data. Four of these components capture interaction, temporal, scale, and shape perspectives, and the fifth component fuses these perspectives together. We also propose a hybrid offline/online training scheme to address concept drift in the data and fulfill the real-time requirements. Combining the estimation model with a graphical user interface, the prototype transaction metric estimation system has demonstrated its potential benefit as a tool for improving a payment processing company's system monitoring capability.

cs.LG↗

arXiv2021

Stress Topology Analysis for Porous Infill Optimization

The optimization of porous infill structures via local volume constraints has become a popular approach in topology optimization. In some design settings, however, the iterative optimization process converges only slowly, or not at all even after several hundreds or thousands of iterations. This leads to regions in which a distinct binary design is difficult to achieve. Interpreting intermediate density values by applying a threshold results in large solid or void regions, leading to sub-optimal structures. We find that this convergence issue relates to the topology of the stress tensor field that is simulated when applying the same external forces on the solid design domain. In particular, low convergence is observed in regions around so-called trisector degenerate points. Based on this observation, we propose an automatic initialization process that prescribes the topological skeleton of the stress field into the material field as solid simulation elements. These elements guide the material deposition around the degenerate points, but can also be remodelled or removed during the optimization. We demonstrate significantly improved convergence rates in a number of use cases with complex stress topologies. The improved convergence is demonstrated for infill optimization under homogeneous as well as spatially varying local volume constraints.

cs.CE↗

arXiv2021

VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this paper, we utilize interactive visualization to increase the interpretability and accessibility of a collection of state-of-the-art debiasing techniques. To aid this, we present Visualization of Embedding Representations for deBiasing system ("VERB"), an open-source web-based visualization tool that helps the users gain a technical understanding and visual intuition of the inner workings of debiasing techniques, with a focus on their geometric properties. In particular, VERB offers easy-to-follow use cases in exploring the effects of these debiasing techniques on the geometry of high-dimensional word vectors. To help understand how various debiasing techniques change the underlying geometry, VERB decomposes each technique into interpretable sequences of primitive transformations and highlights their effect on the word vectors using dimensionality reduction and interactive visual exploration. VERB is designed to target natural language processing (NLP) practitioners who are designing decision-making systems on top of word embeddings, and also researchers working with fairness and ethics of machine learning systems in NLP. It can also serve as a visual medium for education, which helps an NLP novice to understand and mitigate biases in word embeddings.

cs.CL↗

arXiv2020

Merchant Category Identification Using Credit Card Transactions

Digital payment volume has proliferated in recent years with the rapid growth of small businesses and online shops. When processing these digital transactions, recognizing each merchant's real identity (i.e., business type) is vital to ensure the integrity of payment processing systems. Conventionally, this problem is formulated as a time series classification problem solely using the merchant transaction history. However, with the large scale of the data, and changing behaviors of merchants and consumers over time, it is extremely challenging to achieve satisfying performance from off-the-shelf classification methods. In this work, we approach this problem from a multi-modal learning perspective, where we use not only the merchant time series data but also the information of merchant-merchant relationship (i.e., affinity) to verify the self-reported business type (i.e., merchant category) of a given merchant. Specifically, we design two individual encoders, where one is responsible for encoding temporal information and the other is responsible for affinity information, and a mechanism to fuse the outputs of the two encoders to accomplish the identification task. Our experiments on real-world credit card transaction data between 71,668 merchants and 433,772,755 customers have demonstrated the effectiveness and efficiency of the proposed model.

cs.LG↗

arXiv2020

Interactive Focus+Context Rendering for Hexahedral Mesh Inspection

The visual inspection of a hexahedral mesh with respect to element quality is difficult due to clutter and occlusions that are produced when rendering all element faces or their edges simultaneously. Current approaches overcome this problem by using focus on specific elements that are then rendered opaque, and carving away all elements occluding their view. In this work, we make use of advanced GPU shader functionality to generate a focus+context rendering that highlights the elements in a selected region and simultaneously conveys the global mesh structure in the surrounding. To achieve this, we propose a gradual transition from edge-based focus rendering to volumetric context rendering, by combining fragment shader-based edge and face rendering with per-pixel fragment lists. A fragment shader smoothly transitions between wireframe and face-based rendering, including focus-dependent rendering style and depth-dependent edge thickness and halos, and per-pixel fragment lists are used to blend fragments in correct visibility order. To maintain the global mesh structure in the context regions, we propose a new method to construct a sheet-based level-of-detail hierarchy and smoothly blend it with volumetric information. The user guides the exploration process by moving a lens-like hotspot. Since all operations are performed on the GPU, interactive frame rates are achieved even for large meshes.

cs.GR↗

arXiv2020

CNNPruner: Pruning Convolutional Neural Networks with Visual Analytics

Convolutional neural networks (CNNs) have demonstrated extraordinarily good performance in many computer vision tasks. The increasing size of CNN models, however, prevents them from being widely deployed to devices with limited computational resources, e.g., mobile/embedded devices. The emerging topic of model pruning strives to address this problem by removing less important neurons and fine-tuning the pruned networks to minimize the accuracy loss. Nevertheless, existing automated pruning solutions often rely on a numerical threshold of the pruning criteria, lacking the flexibility to optimally balance the trade-off between model size and accuracy. Moreover, the complicated interplay between the stages of neuron pruning and model fine-tuning makes this process opaque, and therefore becomes difficult to optimize. In this paper, we address these challenges through a visual analytics approach, named CNNPruner. It considers the importance of convolutional filters through both instability and sensitivity, and allows users to interactively create pruning plans according to a desired goal on model size or accuracy. Also, CNNPruner integrates state-of-the-art filter visualization techniques to help users understand the roles that different filters played and refine their pruning plans. Through comprehensive case studies on CNNs with real-world sizes, we validate the effectiveness of CNNPruner.

cs.CV↗

arXiv2020

Multi-stream RNN for Merchant Transaction Prediction

Recently, digital payment systems have significantly changed people's lifestyles. New challenges have surfaced in monitoring and guaranteeing the integrity of payment processing systems. One important task is to predict the future transaction statistics of each merchant. These predictions can thus be used to steer other tasks, ranging from fraud detection to recommendation. This problem is challenging as we need to predict not only multivariate time series but also multi-steps into the future. In this work, we propose a multi-stream RNN model for multi-step merchant transaction predictions tailored to these requirements. The proposed multi-stream RNN summarizes transaction data in different granularity and makes predictions for multiple steps in the future. Our extensive experimental results have demonstrated that the proposed model is capable of outperforming existing state-of-the-art methods.

q-fin.ST↗

arXiv2020

Relative global dimensions and stable homotopy categories

In this paper we study the finiteness of global Gorenstein AC-homological dimensions for rings, and answer the questions posed by Becerril, Mendoza, Pérez and Santiago. As an application, we show that any left (or right) coherent and left Gorenstein ring has a projective and injective stable homotopy category, which improves the known result by Beligiannis.

math.RA↗

arXiv2019

InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations

We propose InSituNet, a deep learning based surrogate model to support parameter space exploration for ensemble simulations that are visualized in situ. In situ visualization, generating visualizations at simulation time, is becoming prevalent in handling large-scale simulations because of the I/O and storage constraints. However, in situ visualization approaches limit the flexibility of post-hoc exploration because the raw simulation data are no longer available. Although multiple image-based approaches have been proposed to mitigate this limitation, those approaches lack the ability to explore the simulation parameters. Our approach allows flexible exploration of parameter space for large-scale ensemble simulations by taking advantage of the recent advances in deep learning. Specifically, we design InSituNet as a convolutional regression model to learn the mapping from the simulation and visualization parameters to the visualization results. With the trained model, users can generate new images for different simulation parameters under various visualization settings, which enables in-depth analysis of the underlying ensemble simulations. We demonstrate the effectiveness of InSituNet in combustion, cosmology, and ocean simulations through quantitative and qualitative evaluations.

eess.IV↗