Hybrid$^2$ Neural ODE Causal Modeling and an Application to Glycemic Response
Institute for Computational and Mathematical Engineering, Stanford University(计算与数学工程研究所,斯坦福大学);Broad Institute of MIT and Harvard(哈佛大学与麻省理工学院Broad研究所);Department of Pediatrics, Stanford University(斯坦福大学儿科系);Department of Management Science and Engineering, Stanford University(斯坦福大学管理科学与工程系);Department of Statistics and Department of Computer Science, Stanford University(斯坦福大学统计系与计算机科学系)
Bob Junyi Zou, Matthew E. Levine, Dessi P. Zaharieva, Ramesh Johari, Emily B. Fox
Hybrid models composing mechanistic ODE-based dynamics with flexible and expressive neural network components have grown rapidly in popularity, especially in scientific domains where such ODE-based modeling offers important interpretability and validated causal grounding (e.g., for counterfactual reasoning). The incorporation of mechanistic models also provides inductive bias in standard blackbox modeling approaches, critical when learning from small datasets or partially observed, complex systems. Unfortunately, as the hybrid models become more flexible, the causal grounding provided by the mechanistic model can quickly be lost. We address this problem by leveraging another common source of domain knowledge: \emph{ranking} of treatment effects for a set of interventions, even if the precise treatment effect is unknown. We encode this information in a \emph{causal loss} that we combine with the standard predictive loss to arrive at a \emph{hybrid loss} that biases our learning towards causally valid hybrid models. We demonstrate our ability to achieve a win-win, state-of-the-art predictive performance \emph{and} causal validity, in the challenging task of modeling glucose dynamics post-exercise in individuals with type 1 diabetes.
Causal Discovery from Heteroscedastic Stochastic Dynamical Systems under Imperfect Physical Models
Department of Mechanical & Industrial Engineering(机械与工业工程系);Northeastern University(东北大学);Department of Industrial Engineering and Management Sciences(工业工程与管理科学系);Department of Mechanical Engineering(机械工程系);Northwestern University(西北大学)
Robust Causal Inference for EHR-based Studies of Point Exposures with Missingness in Eligibility Criteria
Harvard T.H. Chan School of Public Health(哈佛陈曾熙公共卫生学院);Harvard Pilgrim Health Care Institute(哈佛皮尔格里姆健康保健研究所);Harvard Medical School(哈佛医学院);Kaiser Permanente Washington Health Research Institute(凯撒永久华盛顿健康研究所);Department of Research & Evaluation, Kaiser Permanente Southern California(凯撒永久南加州研究与评估部);University of California San Francisco(旧金山加利福尼亚大学);University of Washington School of Public Health(华盛顿大学公共卫生学院);University of Pennsylvania(宾夕法尼亚大学)
Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbations
Department of Computer Science, Columbia University, New York, U.S.(哥伦比亚大学计算机科学系);Department of Industrial Engineering and Operations Research, Columbia University, New York, U.S.(哥伦比亚大学工业工程与运筹学系);Department of Applied Mathematics and Applied Physics, Columbia University, New York, U.S.(哥伦比亚大学应用数学与应用物理系);New York Genome Center, New York, U.S.(纽约基因组中心);Irving Institute of Cancer Dynamics, New York, U.S.(伊万·罗伯特癌症动力学研究所);Institute of Computational Biology, Helmholtz Munich, Munich, Germany(海德堡医学院计算生物学研究所);Department of Mathematics, Technische Universität München, Munich, Germany(慕尼黑技术大学数学系)
Dynamic models for estimating the effect of HAART on CD4 in observational studies: application to the Aquitaine Cohort study and the Swiss HIV Cohort Study
在许多随机临床试验中,高效抗逆转录病毒治疗(HAART)已被证明在增加CD 4计数方面有效。因为随机试验有一些局限性(例如,持续时间短,高度选择的受试者),使用观察性研究来评估它是很有趣的。这是具有挑战性的,因为治疗优先在患有重度疾病的受试者中开始,特别是在具有低CD 4计数的受试者中。这个一般性问题已经用依赖于反事实表述的边际结构模型(MSM)来处理。因果关系的另一种方法是基于动态模型。首先,我们提出了三个离散时间动态模型的基础上线性增量(LIM):最简单的模型是由一个差分方程CD 4计数;第二个有一个平衡点;第三个模型是基于一个系统的两个差分方程,允许联合建模CD 4计数和病毒载量。然后,我们考虑连续时间模型的基础上常微分方程的随机效应(ODE-NLME)。这些机制模型允许在可用时并入生物学知识,这导致用于检测处理效应的能力增加。然而,在ODE-NLME模型中的推断从数值的角度来看是具有挑战性的,并且需要特定的方法和软件。LIM在一致性、精确性和复杂性方面是一个有价值的中间选择。不同的方法进行了比较,在模拟和适用于艾滋病毒队列(ANRS CO 3阿基坦队列和瑞士艾滋病毒队列研究)。
Feedback System Neural Networks for Inferring Causality in Directed Cyclic Graphs
University of Bergen(卑尔根大学);isee systems inc.(isee系统公司)
本文提出了一种新的因果网络学习算法(FSNN,Feedback System神经网络),它是在构造和分析非线性常微分方程组的基础上提出的。所构建的系统提供了对负责生成动态系统的过去和潜在未来行为的机制的洞察。它也可以用真实的系统变量来解释,提供了一个整体的,因果准确的,系统的理解现实生活中的相互作用,控制观察到的现象。本文演示了一个n维常微分方程模型,可以参数化,以适应测量数据,使用标准的数值优化技术的生成。该模型利用前馈人工神经网络来捕捉非线性,但在复杂系统中的因果关系网络是一个简约和可解释的表示。所生成的模型可以容易且快速地进行实验和分析,以使用循环重要方法(Schoenberg et. al 2019)。该方法的实用性和适用性的演示给出,表明它产生一个准确的,因果关系正确的模型为三状态,非线性,复杂的动态系统的已知来源。推广到其他动态系统与其他数据源,然后讨论。
Adapting Physics-Informed Neural Networks to Improve ODE Optimization in Mosquito Population Dynamics
School of Computing, Dublin City University(都柏林城市大学计算学院);Faculty of Agriculture, University of Novi Sad(诺威萨大学农业学院);Avia-GIS NV(Avia-GIS NV公司);University of Science, Ho Chi Minh City(胡志明市科学大学);Insight Centre for Data Analytics, Dublin City University(都柏林城市大学洞察数据分析中心)
MODE: Efficient Time Series Prediction with Mamba Enhanced by Low-Rank Neural ODEs
School of Computing and Data Science, The University of Hong Kong(计算与数据科学学院,香港大学);Department of Computing and Data Science, Nanyang Technological University(计算与数据科学系,南洋理工大学);School of Information Engineering, Beijing Institute of Graphic Communication(信息工程学院,北京印刷学院);Department of Computing and Data Science, The University of Hong Kong(计算与数据科学系,香港大学);Yale university(耶鲁大学);University of Cambridge(剑桥大学);Nanyang technological university(南洋理工大学);University of Hong Kong(香港大学)
Neuro-Spectral Architectures for Causal Physics-Informed Networks
École Polytechnique Fédérale de Lausanne (EPFL)(联邦理工学院洛桑校区);Instituto de Matemática Pura e Aplicada (IMPA)(数学与应用数学研究所);Universidade do Estado do Rio de Janeiro (UERJ)(里约热内卢州立大学);Laboratório Nacional de Computação Científica (LNCC)(国家科学计算实验室);University of Georgia (UGA)(佐治亚大学)
Causal Multi-fidelity Surrogate Forward and Inverse Models for ICF Implosions
Theoretical Division, Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室理论 division);Computer, Computational, and Statistical Sciences Division, Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室计算机、计算与统计科学 division)
Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation
University of Texas Rio Grande Valley(德克萨斯大学里奥格兰德河谷分校);University of Maryland(马里兰大学);University of Pittsburgh(匹兹堡大学);Texas A&M University - Corpus Christi(德克萨斯农工大学科珀斯克里斯蒂分校);Emory University(埃默里大学);Lehigh University(利哈伊大学);University of Illinois at Chicago(芝加哥伊利诺伊大学);University of Southern California(南加州大学)
organization= Institute for Risk;Reliability, Leibniz University Hannover , addressline= Callinstraße 34 , city= Hannover , postcode= 30167 , country= Germany;organization= Department of Civil;Environmental Engineering, The Hong Kong Polytechnic University , addressline= Kowloon , city= Hong Kong , country= China;organization= Department of Computing;Mathematical Sciences, California Institute of Technology , city= Pasadena , state= California , country= United States;organization= Guangdong-Hong Kong Joint Research Laboratory for Marine Infrastructure, The Hong Kong Polytechnic University , addressline= Kowloon , city= Hong Kong , country= China;Environmental Engineering, University of Liverpool , city= Liverpool , postcode= L69 3GH , country= United Kingdom;organization= International Joint Research Center for Resilient Infrastructure \& International Joint Research Center for Engineering Reliability;Stochastic Mechanics, Tongji University , city= Shanghai , postcode= 200092 , country= China
Machine Learning Methods for Studying Latent Neural Activity Dynamics
School of Software Engineering, Sun Yat-sen University(中山大学软件工程学院);Department of Computer Science, Cornell University(康奈尔大学计算机科学系);Department of Neurobiology and Behavior, Cornell University(康奈尔大学神经生物学与行为学系);Department of Ecology and Evolutionary Biology, Cornell University(康奈尔大学生态学与进化生物学系);School of Computer Science and Artificial Intelligence, Foshan University(佛山大学计算机科学与人工智能学院)