SHF:Small: More Modular Deep Learning

SHF:Small：更加模块化的深度学习

• 批准号: 2223812
• 负责人: Hridesh Rajan
• 金额: $ 58万
• 依托单位: Iowa State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-10-01 至 2025-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2223812&HistoricalAwards=false
• 关键词: SHF; Small; More; Modular; Deep

This project will study a class of machine learning algorithms known as deep learning that has received much attention in academia and industry. Deep learning has a large number of important societal applications, from self-driving cars to question-answering systems such as Siri and Alexa. A deep learning algorithm uses multiple layers of transformation functions to convert inputs to outputs, each layer learning higher-level of abstractions in the data successively. The availability of large datasets has made it feasible to train deep learning models. Since the layers are organized in the form of a network, such models are also referred to as deep neural networks (DNN). While the jury is still out on the impact of deep learning on the overall understanding of software's behavior, a significant uptick in its usage and applications in wide-ranging areas and safety-critical systems, e.g., autonomous driving, aviation system, medical analysis, etc., combine to warrant research on software engineering practices in the presence of deep learning. One challenge is to enable the reuse and replacement of the parts of a DNN that has the potential to make DNN development more reliable. This project will investigate a comprehensive approach to systematically investigate the decomposition of deep neural networks into modules to enable reuse, replacement, and independent evolution of those modules. A module is an independent part of a software system that can be tested, validated, or utilized without a major change to the rest of the system. Allowing the reuse of DNN modules is expected to reduce energy- and data-intensive training efforts to construct DNN models. Allowing replacement is expected to help replace faulty functionality in DNN models without needing costly retraining steps. The preliminary work of the investigator has shown that it is possible to decompose fully connected neural networks and CNN models into modules and conceptualize the notion of modules. The main goals and the intellectual merits of this project are to further expand this decomposition approach along three dimensions: (1) Does the decomposition approach generalize to large Natural Language Processing (NLP) models, where a huge reduction in CO2e emission is expected? (2) What criteria should be used for decomposing a DNN into modules? A better understanding of the decomposition criteria can help inform the design and implementation of DNNs and reduce the impact of changes. (3) While coarse-grained decomposition has worked well for FCNNs and CNNs, does a finer-grained decomposition of DNNs into modules connected using AND-OR-NOT primitives a la structured decomposition has the potential to both enable more reuse (especially for larger DNNs) and provide deeper insights into the behavior of DNNs? The project also incorporates a rigorous evaluation plan using widely studied datasets. The project is expected to broadly impact society by informing the science and practice of deep learning. A serious problem facing the current software development workforce is that deep learning is widely utilized in our software systems, but scientists and practitioners do not yet have a clear handle on critical problems such as explainability of DNN models, DNN reuse, replacement, independent testing, and independent development. There was no apparent need to investigate the notions of modularity as neural network models trained before the deep learning era were mostly small, trained on small datasets, and were mostly used as experimental features. The notion of DNN modules developed by this project, if successful, could help make significant advances on a number of open challenges in this area. DNN modules could enable the reuse of already trained DNN modules in another context. Viewing a DNN as a composition of DNN modules instead of a black box could enhance the explainability of a DNN's behavior. This project, if successful, will thus have a large positive impact on the productivity of these programmers, the understandability and maintainability of the DNN models that they deploy, and the scalability and correctness of software systems that they produce. Other impacts will include: research-based advanced training as well as enhancement in experimental and system-building expertise of future computer scientists, incorporation of research results into courses at Iowa State University as well as facilitating the integration of modularity research-related topics, and increased opportunities for the participation of underrepresented groups in research-based training.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.

该项目将研究一类被称为深度学习的机器学习算法，该算法在学术界和工业界备受关注。深度学习拥有大量重要的社会应用，从自动驾驶汽车到 Siri 和 Alexa 等问答系统。深度学习算法使用多层转换函数将输入转换为输出，每一层依次学习数据中的更高级别的抽象。大型数据集的可用性使得训练深度学习模型成为可能。由于各层以网络的形式组织，因此此类模型也称为深度神经网络（DNN）。虽然深度学习对软件行为整体理解的影响尚无定论，但其在广泛领域和安全关键系统中的使用和应用显着增加，例如自动驾驶、航空系统、医学分析、等等，结合起来保证了深度学习中软件工程实践的研究。一项挑战是实现 DNN 各部分的重用和替换，这有可能使 DNN 开发更加可靠。该项目将研究一种综合方法，系统地研究深度神经网络分解为模块，以实现这些模块的重用、替换和独立进化。模块是软件系统的独立部分，无需对系统的其余部分进行重大更改即可对其进行测试、验证或使用。允许重复使用 DNN 模块预计将减少构建 DNN 模型所需的能源和数据密集型训练工作。允许替换预计将有助于替换 DNN 模型中的错误功能，而无需昂贵的重新训练步骤。研究人员的前期工作表明，可以将全连接神经网络和 CNN 模型分解为模块，并概念化模块的概念。该项目的主要目标和智力优点是在三个维度上进一步扩展这种分解方法：（1）分解方法是否可以推广到大型自然语言处理（NLP）模型，预计二氧化碳排放量将大幅减少？ (2) 应使用什么标准将 DNN 分解为模块？更好地理解分解标准有助于为 DNN 的设计和实现提供信息，并减少变更的影响。 (3) 虽然粗粒度分解对于 FCNN 和 CNN 来说效果很好，但将 DNN 更细粒度地分解为使用 AND-OR-NOT 原语连接的模块和结构化分解有可能实现更多重用（特别是对于较大的模型） DNN）并提供对 DNN 行为的更深入见解？该项目还采用了广泛研究的数据集制定了严格的评估计划。该项目预计将通过宣传深度学习的科学和实践来广泛影响社会。当前软件开发人员面临的一个严重问题是，深度学习在我们的软件系统中得到了广泛的应用，但科学家和从业者对DNN模型的可解释性、DNN重用、替换、独立测试等关键问题还没有清晰的把握。和自主开发。显然没有必要研究模块化的概念，因为在深度学习时代之前训练的神经网络模型大多很小，在小数据集上训练，并且大多用作实验特征。该项目开发的 DNN 模块概念如果成功，将有助于在该领域的许多开放挑战上取得重大进展。 DNN 模块可以在其他环境中重用已训练的 DNN 模块。将 DNN 视为 DNN 模块的组合而不是黑盒可以增强 DNN 行为的可解释性。该项目如果成功，将对这些程序员的生产力、他们部署的 DNN 模型的可理解性和可维护性，以及他们生产的软件系统的可扩展性和正确性产生巨大的积极影响。其他影响将包括：基于研究的高级培训以及未来计算机科学家的实验和系统构建专业知识的增强，将研究成果纳入爱荷华州立大学的课程以及促进模块化研究相关主题的整合，以及增加了代表性不足的群体参与基于研究的培训的机会。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值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

Mutation-based Fault Localization of Deep Neural Networks

• DOI: 10.1109/ase56229.2023.00171
• 发表时间: 2023-09
• 期刊: 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE)
• 作者: Ali Ghanbari;Deepak-George Thomas;Muhammad Arbab Arshad;Hridesh Rajan

What kinds of contracts do ML APIs need?

• DOI: 10.1007/s10664-023-10320-z
• 发表时间: 2023-07
• 期刊: Empirical Software Engineering
• 影响因子: 4.1
• 作者: S. K. Samantha;Shibbir Ahmed;S. Imtiaz;Hridesh Rajan;G. Leavens

Fix Fairness, Don’t Ruin Accuracy: Performance Aware Fairness Repair using AutoML

• DOI: 10.1145/3611643.3616257
• 发表时间: 2023-06
• 期刊: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
• 作者: Giang Nguyen-;Sumon Biswas;Hridesh Rajan

Fairify: Fairness Verification of Neural Networks

• DOI: 10.1109/icse48619.2023.00134
• 发表时间: 2022-12
• 期刊: 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE)
• 作者: Sumon Biswas;Hridesh Rajan

Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement

• DOI: 10.1109/icse48619.2023.00093
• 发表时间: 2022-12
• 期刊: 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE)
• 作者: S. Imtiaz;Fraol Batole;Astha Singh;Rangeet Pan;Breno Dantas Cruz;Hridesh Rajan