CAREER: Enabling Continual Multi-view Representation Learning: An Adversarial Perspective

职业：实现持续的多视图表示学习：对抗性视角

• 批准号: 2144772
• 负责人: Ming Shao
• 金额: $ 49.9万
• 依托单位: University of Massachusetts, Dartmouth
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-07-15 至 2027-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2144772&HistoricalAwards=false
• 关键词: CAREER; Enabling; Continual; Multi; view

Representation learning techniques attempt to extract and abstract key information (i.e., the features) from raw data to be used in analyses in a wide range of applications, such as cybersecurity, industry, finance, economics, and scientific discovery. As a critical step in machine learning systems, representation learning is meant to be robust in its capacity, regardless of the mutation of raw data due to noises or the variations of raw data caused by capture devices. In the era of big data, representation learning techniques are confronted with new challenges. Massive data collected from different sensors (e.g., the multi-view camera system) or presented in different modalities (e.g., audio-visual-text) have overloaded existing representation learning techniques. In addition, streaming data received from the Internet and sensitive data accumulated over time, such as personal albums and electronic health records, require the established representation learning model to adapt and account for incoming data. This project will develop a robust continual representation learning model to address these challenges. In real-world scenarios where data access is restricted (e.g., sensitive data) or the processing power of devices is limited (e.g., edge and mobile devices), stakeholders will benefit from the adaptive representation learning techniques to enable continual data analyses.This project seeks to advance the fundamental understanding of continual multi-view robust representation learning by integrating machine intelligence and human knowledge in AI-enabled security contexts. There are three unique contributions. First, the project will investigate multi-view consistency pursuit to fuse knowledge and generate a view-invariant representation robust to domain shifts frequently encountered in real-world data. Second, this research will revisit and explore adversarial learning in multi-view contexts to enable new attack modes, including iterative, cross-view, and induced modes. Generated adversarial samples and training procedures will benefit and empower the acquired multi-view representation learning models to mitigate various forms of artificial noise. Third, new continual learning models will be created through a novel Memory Bounded Search Tree to enable the evolution of multi-view representation learning despite continual streams of data. Furthermore, to reduce the search space and uncertainty related to the data, this research will leverage human knowledge to acquire critical annotations and empirical strategies for the proposed continual learning models.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.

表示学习技术试图提取和抽象关键信息（即，这些特征（例如，原始数据中的特征）可用于网络安全、工业、金融、经济和科学发现等广泛应用中的分析。作为机器学习系统中的关键步骤，表示学习意味着其能力是鲁棒的，而不管由于噪声或捕获设备引起的原始数据的变化而导致的原始数据的突变。在大数据时代，表征学习技术面临着新的挑战。从不同传感器收集的大量数据（例如，多视图照相机系统）或以不同的模态呈现（例如，视听文本）已经使现有的表示学习技术过载。此外，从互联网接收的流数据和随着时间的推移积累的敏感数据，如个人相册和电子健康记录，需要建立表示学习模型来适应和解释传入的数据。该项目将开发一个强大的持续表示学习模型来应对这些挑战。在数据访问受到限制的真实场景中（例如，敏感数据）或设备的处理能力有限（例如，边缘和移动的设备），利益相关者将受益于自适应表示学习技术，以实现持续的数据分析。该项目旨在通过在支持AI的安全环境中集成机器智能和人类知识，促进对持续多视图鲁棒表示学习的基本理解。有三个独特的贡献。首先，该项目将研究多视图一致性追求，以融合知识并生成对现实世界数据中经常遇到的域转移具有鲁棒性的视图不变表示。其次，本研究将重新审视和探索多视图环境中的对抗学习，以实现新的攻击模式，包括迭代，交叉视图和诱导模式。生成的对抗性样本和训练过程将使所获得的多视图表示学习模型受益，并使其能够减轻各种形式的人工噪声。第三，新的持续学习模型将通过一种新的内存有界搜索树来创建，以实现多视图表示学习的进化，尽管数据流是连续的。此外，为了减少搜索空间和相关数据的不确定性，这项研究将利用人类知识来获得关键的注释和经验策略，为拟议的持续学习模型。这个奖项反映了NSF的法定使命，并已被认为是值得支持的，通过评估使用基金会的智力价值和更广泛的影响审查标准。

项目成果

Critic-over-Actor-Critic Modeling: Finding Optimal Strategy in ICU Environments

• DOI: 10.1109/bigdata55660.2022.10021125
• 发表时间: 2022-12
• 期刊: 2022 IEEE International Conference on Big Data (Big Data)
• 作者: Riazat Ryan;Ming Shao