III: Medium: Collaborative Research: MUDL: Multidimensional Uncertainty-Aware Deep Learning Framework

III：媒介：协作研究：MUDL：多维不确定性感知深度学习框架

• 批准号: 2107449
• 负责人: Feng Chen
• 金额: $ 50万
• 依托单位: University of Texas at Dallas
• 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 2025-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2107449&HistoricalAwards=false
• 关键词: III; Medium; Collaborative; Research; MUDL

People encounter serious hurdles in finding effective decision-making solutions to real world problems because of uncertainty from a lack of information, conflicting information, and/or unsure observations. Critical safety concerns have been consistently highlighted because how to interpret this uncertainty has not been carefully investigated. If the uncertainty is misinterpreted, this can result in unnecessary risk. For example, a self-driving autonomous car can misdetect a human in the road. An artificial intelligence-based medical assistant may misdiagnose cancer as a benign tumor. Further, a phishing email can be detected as a normal email. The consequences of all these misdetections or misclassifications caused by different types of uncertainty adds risk and potential adverse events. Artificial intelligence (AI) researchers have actively explored how to solve various decision-making problems under uncertainty. However, no prior research has looked into how different approaches of studying uncertainty in AI can leverage each other. This project studies how to measure different causes of uncertainty and use them to solve diverse decision-making problems more effectively. This project can help develop trustworthy AI algorithms that can be used in many real world decision-making problems. In addition, this project is highly transdisciplinary so that it can encourage broader, newer, and more diverse approaches. To magnify the impact of this project in research and education, this project leverages multicultural, diversity, and STEM programs for students with diverse backgrounds and under-represented populations. This project also includes seminar talks, workshops, short courses, and/or research projects for high school and community college students. This project aims to develop a suite of deep learning (DL) techniques by considering multiple types of uncertainties caused by different root causes and employ them to maximize the effectiveness of decision-making in the presence of highly intelligent, adversarial attacks. This project makes a synergistic but transformative research effort to study: (1) how different types of uncertainties can be quantified based on belief theory; (2) how the estimates of different types of uncertainties can be considered in DL-based approaches; and (3) how multiple types of uncertainties influence the effectiveness and efficiency of decision-making in high-dimensional, complex problems. This project advances the state-of-the-art research by performing the following: (1) Proposing a scalable, robust unified DL-based framework to effectively infer predictive multidimensional uncertainty caused by heterogeneous root causes in adversarial environments. (2) Dealing with multidimensional uncertainty based on neural networks. (3) Enhancing both decision effectiveness and efficiency by considering multidimensional uncertainty-aware designs. (4) Testing proposed approaches to ensure their robustness in the presence of intelligent adversarial attackers with advanced deception tactics based on both simulation models and visualization tools.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.

由于信息缺乏、信息冲突和/或不确定的观察带来的不确定性，人们在寻找现实世界问题的有效决策解决方案时遇到严重障碍。 关键的安全问题一直被强调，因为如何解释这种不确定性尚未得到仔细研究。如果不确定性被误解，可能会导致不必要的风险。例如，自动驾驶汽车可能会错误地检测到路上的行人。基于人工智能的医疗助理可能会将癌症误诊为良性肿瘤。 此外，网络钓鱼电子邮件可以被检测为正常电子邮件。 由不同类型的不确定性引起的所有这些错误检测或错误分类的后果增加了风险和潜在的不良事件。 人工智能（AI）研究人员积极探索如何解决不确定性下的各种决策问题。 然而，之前没有研究探讨研究人工智能不确定性的不同方法如何相互利用。 该项目研究如何衡量不确定性的不同原因，并利用它们更有效地解决各种决策问题。 该项目可以帮助开发值得信赖的人工智能算法，可用于许多现实世界的决策问题。此外，该项目具有高度跨学科性，因此可以鼓励更广泛、更新和更多样化的方法。 为了扩大该项目在研究和教育方面的影响，该项目利用多元文化、多样性和 STEM 项目，为具有不同背景和代表性不足的人群的学生提供服务。该项目还包括为高中生和社区学院学生举办研讨会、讲习班、短期课程和/或研究项目。 该项目旨在通过考虑不同根本原因引起的多种类型的不确定性来开发一套深度学习（DL）技术，并利用它们在存在高度智能的对抗性攻击时最大限度地提高决策的有效性。 该项目做出了一项协同但变革性的研究工作，旨在研究：（1）如何基于信念理论量化不同类型的不确定性； (2) 在基于深度学习的方法中如何考虑不同类型不确定性的估计； (3)多种类型的不确定性如何影响高维、复杂问题决策的有效性和效率。该项目通过执行以下操作来推进最先进的研究：（1）提出一个可扩展、强大的基于深度学习的统一框架，以有效推断对抗环境中由异构根本原因引起的预测多维不确定性。 (2)基于神经网络处理多维不确定性。 (3)通过考虑多维不确定性感知设计来提高决策有效性和效率。 (4) 测试所提出的方法，以确保其在面对智能对抗攻击者时具有鲁棒性，并采用基于模拟模型和可视化工具的先进欺骗策略。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优势进行评估，被认为值得支持以及更广泛的影响审查标准。

项目成果

Interactive Web-Based Visual Analysis on Network Traffic Data

基于交互式网络的网络流量数据可视化分析

• DOI: 10.3390/info14010016
• 发表时间: 2023
• 期刊: Information
• 影响因子: 3.1
• 作者: Jeong, Dong Hyun;Cho, Jin-Hee;Chen, Feng;Kaplan, Lance;Jøsang, Audun;Ji, Soo-Yeon
• 通讯作者: Ji, Soo-Yeon

A survey on uncertainty reasoning and quantification in belief theory and its application to deep learning

• DOI: 10.1016/j.inffus.2023.101987
• 发表时间: 2023-08
• 期刊: Inf. Fusion
• 作者: Zhen Guo;Zelin Wan;Qisheng Zhang;Xujiang Zhao;Qi Zhang;L. Kaplan;A. Jøsang;Dong-Ho Jeong

Multi-Label Temporal Evidential Neural Networks for Early Event Detection

• DOI: 10.1109/icassp49357.2023.10096305
• 发表时间: 2023-06
• 期刊: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
• 作者: Xujiang Zhao;Xuchao Zhang;Chengli Zhao;Jinny Cho;L. Kaplan;D. Jeong;A. Jøsang;Haifeng Chen;F. Chen

Active Learning on Neural Networks through Interactive Generation of Digit Patterns and Visual Representation

• DOI: 10.1109/isec57711.2023.10402169
• 发表时间: 2023-03
• 期刊: 2023 IEEE Integrated STEM Education Conference (ISEC)
• 作者: Dong H. Jeong;Jin-Hee Cho;Feng Chen;A. Jøsang;Soo-Yeon Ji

How Out-of-Distribution Data Hurts Semi-Supervised Learning

• DOI: 10.1109/icdm54844.2022.00087
• 发表时间: 2020-10
• 期刊: 2022 IEEE International Conference on Data Mining (ICDM)
• 作者: Xujiang Zhao;Killamsetty Krishnateja;Rishabh K. Iyer;Feng Chen