III: Medium: Collaborative Research: Principled Uncertainty Quantification in Deep Learning Models for Time Series Analysis

III：媒介：协作研究：用于时间序列分析的深度学习模型中的原则性不确定性量化

• 批准号: 2106961
• 负责人: Chao Zhang
• 金额: $ 67.53万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Continuing 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=2106961&HistoricalAwards=false
• 关键词: III; Medium; Collaborative; Research; Principled

Time series data are ubiquitous in modern science and engineering. An unprecedented amount is being collected in diverse applications such as healthcare systems, the Web, cyber network monitoring, self-driving cars, and Internet-of-Things services. While deep learning has achieved enormous success in time series predictive analysis, a key bottleneck of such models is that they are ignorant about the uncertainties in their predictions. A consequence is that they can produce wildly wrong predictions without noticing---this will lead to misguided decisions, which can be catastrophic in life-critical applications. This project aims to remedy this issue and advance deep learning towards more trustworthy time series analysis. The project will enable principled deep learning models for uncertainty-aware and reliable time series regression and classification without sacrificing their predictive power. Research findings from the project will be incorporated into graduate-level classes, tutorials, and workshops to bring multiple stakeholders and domain scientists together.The technical aims of this project are divided into three thrusts. First, the project will develop novel techniques bridging deep sequential models (e.g., recurrent networks, transformers) with Gaussian processes to quantify uncertainty in the functional space. Second, the project will explore how to learn calibrated deep sequential models and how to further decouple different sources of uncertainties to understand where a model's predictive uncertainty comes from. Third, the project will harness uncertainty to improve the reliability and efficiency of time series predictive systems. These techniques will enjoy the representation power of deep neural networks for modeling complex temporal dependencies in time-series data, while providing principled methodologies for quantifying and leveraging uncertainty for robustness and performance. The developed new models, algorithms, and techniques will be deployed in two important applications for times series analysis: 1) public health monitoring and forecasting, and 2) real-time analysis for mobile sensing time series data. The developed tools will also be open-sourced for trustworthy time series analysis that can benefit many other applications.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.

时间序列数据在现代科学和工程中是无处不在的。在医疗保健系统、网络、网络监控、自动驾驶汽车和物联网服务等各种应用中收集的数据达到了前所未有的水平。虽然深度学习在时间序列预测分析中取得了巨大的成功，但此类模型的一个关键瓶颈是它们对预测中的不确定性一无所知。一个后果是，它们可能会在没有察觉的情况下产生非常错误的预测-这将导致错误的决定，这在至关重要的应用程序中可能是灾难性的。这个项目旨在解决这个问题，并推动深度学习向更可信的时间序列分析迈进。该项目将使有原则的深度学习模型能够在不牺牲其预测能力的情况下，实现对不确定性的感知和可靠的时间序列回归和分类。该项目的研究成果将被纳入研究生级别的课程、教程和研讨会，以将多个利益相关者和领域科学家聚集在一起。该项目的技术目标分为三个方面。首先，该项目将开发新的技术，将深层序列模型(例如，递归网络、变压器)与高斯过程连接起来，以量化功能空间中的不确定性。其次，该项目将探索如何学习校准的深度序列模型，以及如何进一步分离不同的不确定性来源，以了解模型的预测不确定性来自哪里。第三，该项目将利用不确定性来提高时间序列预测系统的可靠性和效率。这些技术将享受深度神经网络的表示能力，用于对时间序列数据中复杂的时间相关性进行建模，同时提供量化和利用不确定性的原则性方法，以提高稳健性和性能。开发的新模型、算法和技术将部署在时间序列分析的两个重要应用中：1)公共健康监测和预测，2)移动传感时间序列数据的实时分析。开发的工具也将是开源的，用于可信的时间序列分析，可以使许多其他应用程序受益。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Actionable Insights in Urban Multivariate Time-series

• DOI: 10.1145/3459637.3482410
• 发表时间: 2021-10
• 期刊: Proceedings of the 30th ACM International Conference on Information & Knowledge Management
• 作者: Anika Tabassum;S. Chinthavali;Varisara Tansakul;B. Prakash

Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States.

• DOI: 10.1073/pnas.2113561119
• 发表时间: 2022-04-12
• 期刊: Proceedings of the National Academy of Sciences of the United States of America
• 影响因子: 11.1

Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future

Back2Future：利用回填动态改进未来的实时预测

• 发表时间: 2022
• 期刊: International Conference on Learning Representations (ICLR
• 作者: Kamarthi, Harshavardhan;Rodriguez, Alexander;Prakash, B. Aditya
• 通讯作者: Prakash, B. Aditya

Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition

• DOI: 10.1145/3534678.3539247
• 发表时间: 2022-05
• 期刊: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Yinghao Li;Le Song;Chao Zhang

Autoregressive Diffusion Model for Graph Generation

• DOI: 10.48550/arxiv.2307.08849
• 发表时间: 2023-07
• 作者: Lingkai Kong;Jiaming Cui;Haotian Sun;Yuchen Zhuang;B. Prakash;Chao Zhang