How can we learn a dynamical system to make forecasts, when some variables are unobserved? For instance, in COVID-19, we want to forecast the number of infected and death cases but we do not know the count of susceptible and exposed people. While mechanics compartment models are widely used in epidemic modeling, data-driven models are emerging for disease forecasting. We first formalize the learning of physics-based models as AutoODE, which leverages automatic differentiation to estimate the model parameters. Through a benchmark study on COVID-19 forecasting, we notice that physics-based mechanistic models significantly outperform deep learning. Our method obtains a 57.4% reduction in mean absolute errors for 7-day ahead COVID-19 forecasting compared with the best deep learning competitor. Such performance differences highlight the generalization problem in dynamical system learning due to distribution shift. We identify two scenarios where distribution shift can occur: changes in data domain and changes in parameter domain (system dynamics). Through systematic experiments on several dynamical systems, we found that deep learning models fail to forecast well under both scenarios. While much research on distribution shift has focused on changes in the data domain, our work calls attention to rethink generalization for learning dynamical systems.
Generative Example-Based Explanations: Bridging the Gap between Generative Modeling and Explainability
Center for Artificial Intelligence and Robotics(人工智能与机器人中心);Technical University of Applied Sciences Würzburg-Schweinfurt(应用科学大学魏玛-施维林分校);Bielefeld University(比勒菲尔德大学)
JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation
Kognia Sports Intelligence(Kognia体育智能);Visual Intelligence for Transportation, EPFL(交通视觉智能,EPFL);Institut de Robòtica i Informàtica Industrial, CSIC-UPC(机器人与信息工业研究所,CSIC-UPC)
Context-Enhanced Multi-View Trajectory Representation Learning: Bridging the Gap through Self-Supervised Models
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Nanyang Technological University(南洋理工大学)
Atomistic Modeling of Chemical Disorder in Materials: Bridging Conventional Methods and AI-Assisted Approaches
Department of Materials Design and Innovation, University at Buffalo(布法罗大学材料设计与创新系);Department of Materials Science and Engineering, National University of Singapore(新加坡国立大学材料科学与工程系)
FlowCritic: Bridging Value Estimation with Flow Matching in Reinforcement Learning
School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China(电子科技大学机械与电子工程学院);School of Information Science and Technology, ShanghaiTech University(上海科技大学信息科学与技术学院);School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电子与电气工程学院)
Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
School of Computer Science and Engineering, Southeast University, Nanjing, China(东南大学计算机科学与工程学院);Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China(新一代人工智能技术及其交叉应用国家重点实验室)