CRII: RI: Self-Attention through the Bayesian Lens

自关注（Self-attention）是最近引入的一种增强神经网络架构的方法，它极大地提高了神经网络在一系列应用中的性能，特别是自然语言处理和计算机视觉。从概念上讲，人类大脑通过学习有选择地关注最显著的元素来处理复杂的视觉信息，自我关注提高了网络捕捉数据中长期关系的能力。然而，对自注意网络输出的不确定性进行量化的研究有限，尽管不确定性量化对于可靠的学习模型至关重要。自关注网络的不确定性很大程度上取决于网络关注的对象。该项目将模拟与注意力放置相关的不确定性，从而更好地量化网络输出中的不确定性。该研究还将利用统计方法将部分架构设计转换为标准计算程序，从而促进新网络架构的设计。该项目的第二个目标是将自注意机制应用于统计推断以提高计算效率。最终，该项目将产生更可靠、更广泛适用的新网络架构。这项研究还将支持为塔夫茨大学的研究生和本科生开发深度学习课程。本项目使用贝叶斯方法研究自注意网络，并提出了一种新的修改-贝叶斯自注意网络（bsan）。自注意网络使用“注意权重”从特定范围的数据中获取信息，而bsan为注意权重分配概率。通过对注意力中的不确定性进行建模，bsan自然继承了贝叶斯方法的理想特性，如更好的不确定性估计和更少的数据过拟合。bsan将自动计算注意概率作为统计推理程序，简化新的基于注意的神经网络的设计，它只需要确定注意结构的位置。bsan的研究将产生新的网络架构，有可能在自然语言处理和图形数据分析的广泛任务中提高可靠性。除了bsan之外，本项目还将使用自注意机制来构建涉及大量变量的概率分布。所构造的分布具有灵活性和计算效率高的特点，适用于大规模统计推断中的分布近似。该项目将为高斯过程提供计算效率高的推理方法，高斯过程是机器学习和其他相关领域广泛使用的模型。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Self-attention, a recently introduced augmentation to neural network architectures, has greatly improved neural network performance in a range of applications, particularly natural language processing and computer vision. Based conceptually on the way the human brain processes complex visual information by learning to selectively focus on the most salient elements, self-attention improves network ability to capture long-range relations in data. However, there is limited study in quantifying uncertainties of the outputs of self-attention networks, though uncertainty quantification is critically important for reliable learning models. The uncertainty of a self-attention network highly depends on where the network pays its attention to. This project will model the uncertainties associated with attention placement, and thereby better quantify the uncertainty in network outputs. The research will also convert part of the architecture design to standard computational procedures by utilizing statistical methods, and thus facilitate the design of new network architectures. This project has a secondary aim of applying the self-attention mechanism to statistical inference for computational efficiency. Ultimately, this project will produce new network architectures that are more reliable and more broadly applicable. This research will also support the development of a deep learning course for both graduate and undergraduate students at Tufts University. This project examines self-attention networks using a Bayesian approach and proposes a new modification - Bayesian Self-Attention Networks (BSANs). While self-attention networks use "attention weights" to take information from a special range of the data, BSANs assign probabilities to attention weights. By modeling uncertainties in the attention, BSANs naturally inherit desirable properties of Bayesian methods, such as better estimations of uncertainties and less overfitting of data. BSANs will automate the computation of attention probabilities as statistical inference procedures, simplifying the design of new attention-based neural networks, which will only need to determine where to place the attention structure. The study of BSANs will result in new network architectures, with the potential to improve reliability over a wide span of tasks in both natural language processing and graph data analysis. In addition to BSANs, this project will also use the self-attention mechanism to construct probability distributions that involve large numbers of variables. Being flexible and computationally efficient, the constructed distributions will be suitable for distribution approximation in large-scale statistical inference. This project will produce computationally efficient inference methods for Gaussian processes, a widely used model in machine learning and other related areas.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.