Many real-world situations allow for the acquisition of additional relevant information when making an assessment with limited or uncertain data. However, traditional ML approaches either require all features to be acquired beforehand or regard part of them as missing data that cannot be acquired. In this work, we propose models that dynamically acquire new features to further improve the prediction assessment. To trade off the improvement with the cost of acquisition, we leverage an information theoretic metric, conditional mutual information, to select the most informative feature to acquire. We leverage a generative model, arbitrary conditional flow (ACFlow), to learn the arbitrary conditional distributions required for estimating the information metric. We also learn a Bayesian network to accelerate the acquisition process. Our model demonstrates superior performance over baselines evaluated in multiple settings.
Stochastic Encodings for Active Feature Acquisition
Department of Computer Science and Technology, University of Cambridge, Cambridge, United Kingdom（计算机科学与技术系，剑桥大学，剑桥，英国）；Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, United Kingdom（应用数学与理论物理系，剑桥大学，剑桥，英国）；Department of Statistics, University of Oxford, Oxford, United Kingdom（统计学系，牛津大学，牛津，英国）；Department of Artificial Intelligence, Korea University, Seoul, Korea（人工智能系，韩国大学，首尔，韩国）
Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information
ETH Zurich（苏黎世联邦理工学院）；ETH AI Center（苏黎世联邦理工学院人工智能中心）；Helmholtz AI（亥姆霍兹人工智能研究所）；Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Discussion: "Bayesian Optimal Design of Experiments for Inferring the Statistical Expectation of Expensive Black-Box Functions" (Pandita, P., Bilionis, I., and Panchal, J., 2019. ASME. J. Mech. Des. 141(10): 101404)
Consistent Learning-to-Defer with Expert-Conditional Advice
School of Computing（计算学院）；Département de Mathématiques（数学系）；National University of Singapore（新加坡国立大学）；Sorbonne University（索邦大学）；Fédération ENAC（ENAC联合会）；ISAE-SUPAERO；ONERA；Agency for Science, Technology and Research（科技研究局）；Université de Toulouse（图卢兹大学）；Institute for Infocomm Research（信息与通信研究所）
Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
Department of Mathematics and Systems Engineering（数学与系统工程系）；Department of Biomedical Engineering & Science（生物医学工程与科学系）；Florida Institute of Technology（佛罗里达理工学院）；A. A. Martinos Center for Biomedical Imaging（A.A. Martinos生物医学成像中心）；Massachusetts General Hospital/Harvard Medical School（麻省总医院/哈佛医学院）；Department of Radiology（放射科）；Embry-Riddle Aeronautical University（艾姆伯-里尔航空大学）
BRiG-AFA: Bellman Risk-to-Go Learning for Non-Myopic Active Feature Acquisition
Curtin Business School, Curtin University（科廷大学科廷商学院）；School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University（科廷大学电气、计算与数学科学学院）
Towards generalizable single-cell perturbation modeling via the Conditional Monge Gap
IBM Research Europe（欧洲IBM研究院）；ETH Zürich（苏黎世联邦理工学院）；Lausanne University Hospital and University of Lausanne（洛桑大学医院与洛桑大学）；Swiss Institute of Bioinformatics (SIB)（瑞士生物信息学研究所）
EnvCDiff: Joint Refinement of Environmental Information and Channel Fingerprints via Conditional Generative Diffusion Model
National Mobile Communications Research Laboratory, Southeast University（东南大学国家移动通信研究中心）；Purple Mountain Laboratories（紫金山实验室）；Department of Electrical and Computer Engineering, University of Delaware（德雷塞尔大学电气与计算机工程系）
Simulating Dynamic Tumor Contrast Enhancement in Breast MRI using Conditional Generative Adversarial Networks
Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM)（巴塞罗那人工智能医学实验室）；Departament de Matemàtiques i Informàtica, Universitat de Barcelona（巴塞罗那大学数学与计算机科学系）；Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich（生物医学成像机器学习研究所，海德堡慕尼黑）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑技术大学计算、信息与技术学院）；Department of Oncology-Pathology, Karolinska Institutet（卡罗林斯卡研究所肿瘤-病理学系）；School of Biomedical Engineering & Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与成像科学学院）
Channel Fingerprint Construction for Massive MIMO: A Deep Conditional Generative Approach
National Mobile Communications Research Laboratory, Southeast University（东南大学国家移动通信研究中心）；Purple Mountain Laboratories（紫金山实验室）；State Key Laboratory of CNS/ATM, Beijing Institute of Technology（北京理工大学 CNS/ATM 国家重点实验室）；Beijing Institute of Technology（北京理工大学）；MIT Key Laboratory of Complex-Field Intelligent Sensing, Beijing Institute of Technology（MIT 复杂场智能感知实验室，北京理工大学）；Advanced Technology Research Institute, Beijing Institute of Technology（北京理工大学先进技术研究院）；Yangtze Delta Region Academy, Beijing Institute of Technology（长江三角洲地区研究院，北京理工大学）；Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电子与电气工程系）；Department of Electrical and Computer Engineering, University of Delaware（德雷塞尔大学电子与计算机工程系）
