FMitF: Track I: Formal Methods for Explainable Machine Learning

FMITF：第一轨：可解释机器学习的形式化方法

基本信息

批准号：
1918211
负责人：
Loris DAntoni
金额：
$ 75万
依托单位：
University of Wisconsin-Madison
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-10-01 至 2024-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1918211&HistoricalAwards=false
关键词：
FMitF Track Formal Methods Explainable

项目摘要

Artificial intelligence, in the form of machine learning (ML), is rapidly transforming the world. Today, ML is responsible for an ever-growing spectrum of sensitive decisions from loan decisions, to diagnosing diseases, to autonomous driving. With ML spreading across many industries, the issue of explainability, i.e., explaining the decisions of opaque models in ML, has taken center stage. Despite much interest and progress in the explainability question, the research in the area is still nascent and does not capture the full spectrum of ML models used in practice and the forms of explanation that are of interest to users and subjects of those models. This project explores a range of explanation tasks can be enabled by (and benefit from) program-synthesis technology as developed by the formal-methods community. The project's impact is to lay logical foundations for explainability of AI decisions, and thus has the potential to ensure transparency in our increasingly autonomous world. The project's novelty is to use program synthesis to automatically construct simple, coherent, human-readable explanations, in the form of high-level programs, of a ML model or its decisions. The project investigates techniques for synthesizing actionable explanations of the decisions made by a traditional (non-sequence) ML models as well as recurrent models. From a technical viewpoint, this project develops new program-synthesis techniques that leverage optimization technologies and apply them to the unique problem setup presented by explainable machine learning. Second, the project develops algorithms for automata learning, synthesis of regular expressions, and synthesis of temporal-logic formulae and uses them to explain the predictions of sequence 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.

机器学习 (ML) 形式的人工智能正在迅速改变世界。如今，机器学习负责越来越多的敏感决策，从贷款决策到诊断疾病，再到自动驾驶。随着机器学习在许多行业的普及，可解释性问题，即解释机器学习中不透明模型的决策，已成为焦点。尽管人们对可解释性问题很感兴趣并取得了很大进展，但该领域的研究仍处于起步阶段，并未涵盖实践中使用的机器学习模型的全部范围以及这些模型的用户和主题感兴趣的解释形式。该项目探索了一系列可由形式方法社区开发的程序合成技术实现（并从中受益）的解释任务。该项目的影响是为人工智能决策的可解释性奠定逻辑基础，从而有可能确保我们日益自治的世界的透明度。该项目的新颖之处在于使用程序合成以高级程序的形式自动构建简单、连贯、人类可读的解释，对 ML 模型或其决策进行解释。该项目研究了对传统（非序列）机器学习模型以及循环模型做出的决策进行综合可行解释的技术。从技术角度来看，该项目开发了新的程序合成技术，利用优化技术并将其应用于可解释的机器学习提出的独特问题设置。其次，该项目开发了自动机学习、正则表达式合成和时序逻辑公式合成的算法，并用它们来解释序列模型的预测。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。

项目成果

期刊论文数量（13）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Synthesizing Action Sequences for Modifying Model Decisions

综合修改模型决策的动作序列

DOI：
发表时间：
2020-01
期刊：
Association for the Advancement of Artificial Intelligence
影响因子：
0
作者：
Ramakrishnan, Goutham;Lee, Yun Chan;Albarghouthi, Aws
通讯作者：
Albarghouthi, Aws

Deep Unlearning via Randomized Conditionally Independent Hessians

通过随机条件独立 Hessians 进行深度忘却

DOI：
发表时间：
2022-01
期刊：
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
影响因子：
0
作者：
Mehta, Ronak R.;Pal, Sourav;Singh, Vikas;Ravi, Sathya N.
通讯作者：
Ravi, Sathya N.

Adaptive Activation Thresholding: Dynamic Routing Type Behavior for Interpretability in Convolutional Neural Networks

自适应激活阈值：卷积神经网络中可解释性的动态路由类型行为

DOI：
10.1109/iccv.2019.00504
发表时间：
2019-10-01
期刊：
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
影响因子：
0
作者：
Yiyou Sun;Sathya Ravi;Vikas Singh
通讯作者：
Vikas Singh

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets

等方差允许在分析汇集的神经影像数据集时处理多个有害变量

DOI：
2203.15234
发表时间：
2022-06
期刊：
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR
影响因子：
0
作者：
Lokhande, Vishnu Suresh;Chakraborty, Rudrasis;Ravi, Sathya N.;Singh, Vikas
通讯作者：
Singh, Vikas

The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions

数据集多重性问题：不可靠的数据如何影响预测