III: Small: DeepRep: Unsupervised Deep Representation Learning for Scientific Data Analysis and Visualization

III：小：DeepRep：用于科学数据分析和可视化的无监督深度表示学习

• 批准号: 2101696
• 负责人: Chaoli Wang
• 金额: $ 49.99万
• 依托单位: University of Notre Dame
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2101696&HistoricalAwards=false
• 关键词: III; Small; DeepRep; Unsupervised; Deep

Learning features or representations from data is a longstanding goal of data mining and machine learning. In scientific visualization, feature definitions are usually application-specific, and in many cases, they are vague or even unknown. Representation learning is often the first and crucial step toward effective scientific data analysis and visualization (SDAV). This step has become increasingly important and necessary as the size and complexity of scientific simulation data continue to grow. For more than three decades, manual feature engineering has been the standard practice in scientific visualization. With the thriving of AI and machine learning, leveraging deep neural networks for automatic feature discovery has emerged as a promising and reliable alternative. The overarching goal of this project is to develop DeepRep, a systematic deep representation learning framework for SDAV. The outcomes will provide a paradigm shift to best represent scientific data in the abstract feature space, helping scientists better understand various physical, chemical, and medical phenomena such as those from climate, combustion, and cardiovascular applications. This project thus serves the national interest, as stated by NSF's mission: to promote the progress of science; to advance the national health, prosperity, and welfare.SDAV mainly deals with unlabeled data. Therefore, the project team will investigate unsupervised learning techniques and explore their uses in learning abstract, deep, and expressive features. The proposed framework considers a broad range of inputs, including three-dimensional scalar and vector data and their visual representations (i.e., line, surface, and subvolume). Specifically, the team will study different unsupervised deep representation learning techniques, including distributed learning, disentangled learning, and self-supervised learning. The DeepRep project aims to demonstrate their utility in various subsequent SDAV tasks, such as dimensionality reduction, data clustering, representative selection, anomaly detection, data classification, and data generation. The proposed research includes four primary tasks: (1) autoencoders for distributed learning of volumetric data and their visual representations, (2) graph convolutional networks for representation learning of surface data to support node-level and graph-level operations, (3) ensemble data generation from independent features via disentangled learning, and (4) self-supervised solutions for robust data representation via contrastive learning. Furthermore, the team will perform comprehensive objective and subjective evaluations using multilevel metrics to evaluate the framework's effectiveness.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

来自数据的学习功能或表示形式是数据挖掘和机器学习的长期目标。在科学可视化中，特征定义通常是特定于应用的，并且在许多情况下，它们含糊不清甚至未知。表示学习通常是朝着有效的科学数据分析和可视化（SDAV）迈出的第一步。随着科学仿真数据的规模和复杂性不断增长，此步骤变得越来越重要和必要。在过去的三十多年中，手动功能工程一直是科学可视化的标准实践。随着人工智能和机器学习的繁荣，利用深层神经网络进行自动特征发现已成为一种有前途且可靠的替代方案。该项目的总体目标是开发DeepRep，这是SDAV的系统性深度表示学习框架。结果将提供范式转变，以最好地代表抽象特征空间中的科学数据，从而帮助科学家更好地了解各种物理，化学和医学现象，例如气候，燃烧和心血管应用。正如NSF的使命所指出的那样：促进科学的进步；为了促进国家健康，繁荣和福利。SDAV主要处理未标记的数据。因此，项目团队将研究无监督的学习技术，并探索他们在学习抽象，深度和表现力特征中的用途。所提出的框架考虑了广泛的输入，包括三维标量和向量数据及其视觉表示（即线，表面和子体积）。具体来说，团队将研究不同的无监督的深度表示学习技术，包括分布式学习，分散的学习和自我监督的学习。 DeepRep项目旨在在随后的各种SDAV任务中展示其实用性，例如降低维度，数据聚类，代表性选择，异常检测，数据分类和数据生成。拟议的研究包括四个主要任务：（1）用于分布体积数据及其视觉表示的自动编码器，（2）图形卷积网络，用于表示表面数据的表示，以支持节点级别和图形级操作，（3）通过无用的学习从独立特征中从独立的特征中生成的配乐数据，以及（4）自我掩盖的解决方案，可通过强大的学习代表来进行反对。此外，该团队将使用多级指标进行全面的客观和主观评估，以评估框架的有效性。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子和更广泛影响的评估评估来审查标准的。

项目成果

Reconstructing Unsteady Flow Data From Representative Streamlines via Diffusion and Deep-Learning-Based Denoising

• DOI: 10.1109/mcg.2021.3089627
• 发表时间: 2021-11-01
• 期刊: IEEE COMPUTER GRAPHICS AND APPLICATIONS
• 影响因子: 1.8
• 作者: Gu, Pengfei;Han, Jun;Wang, Chaoli
• 通讯作者: Wang, Chaoli

VCNet: A generative model for volume completion

• DOI: 10.1016/j.visinf.2022.04.004
• 发表时间: 2022-04
• 期刊: Vis. Informatics
• 作者: Jun Han;Chaoli Wang

NeRVI: Compressive neural representation of visualization images for communicating volume visualization results

• DOI: 10.1016/j.cag.2023.08.024
• 发表时间: 2023-08
• 期刊: Comput. Graph.
• 作者: Pengfei Gu;Da Chen;Chaoli Wang

Hierarchical Sankey Diagram: Design and Evaluation

分层桑基图：设计和评估

• DOI: 10.1007/978-3-030-90436-4_31
• 发表时间: 2021
• 期刊: International Symposium on Visual Computing
• 作者: Porter, William P;Murphy, Conor P;Williams, Dane R;O'Handley, Brendan J.;Wang, Chaoli
• 通讯作者: Wang, Chaoli

STNet: An End-to-End Generative Framework for Synthesizing Spatiotemporal Super-Resolution Volumes

• DOI: 10.1109/tvcg.2021.3114815
• 发表时间: 2021-09
• 期刊: IEEE Transactions on Visualization and Computer Graphics
• 影响因子: 5.2
• 作者: Jun Han;Hao Zheng;D. Chen;Chaoli Wang