Machine learning methods have greatly changed science, engineering, finance, business, and other fields. Despite the tremendous accomplishments of machine learning and deep learning methods, many challenges still remain. In particular, the performance of machine learning methods is often severely affected in case of diverse data, usually associated with smaller data sets or data related to areas of study where the size of the data sets is constrained by the complexity and/or high cost of experiments. Moreover, data with limited labeled samples is a challenge to most learning approaches. In this paper, the aforementioned challenges are addressed by integrating graph-based frameworks, multiscale structure, modified and adapted optimization procedures and semi-supervised techniques. This results in two innovative multiscale Laplacian learning (MLL) approaches for machine learning tasks, such as data classification, and for tackling diverse data, data with limited samples and smaller data sets. The first approach, called multikernel manifold learning (MML), integrates manifold learning with multikernel information and solves a regularization problem consisting of a loss function and a warped kernel regularizer using multiscale graph Laplacians. The second approach, called the multiscale MBO (MMBO) method, introduces multiscale Laplacians to a modification of the famous classical Merriman-Bence-Osher (MBO) scheme, and makes use of fast solvers for finding the approximations to the extremal eigenvectors of the graph Laplacian. We demonstrate the performance of our methods experimentally on a variety of data sets, such as biological, text and image data, and compare them favorably to existing approaches.
Towards Efficient Training of Graph Neural Networks: A Multiscale Approach
Faculty of Computer and Information Science(计算机与信息科学学院);Ben-Gurion University of the Negev(本· Gurion 内盖夫大学);Department of Applied Mathematics and Theoretical Physics(应用数学与理论物理系);University of Cambridge(剑桥大学);Department of Earth, Ocean and Atmospheric Sciences(地球、海洋与大气科学系);University of British Columbia(不列颠哥伦比亚大学);Pidstryhach Institute for Applied Problems of Mechanics and Mathematics(应用力学与数学问题研究所);NAS of Ukraine, L’viv, Ukraine(乌克兰国家科学院,利沃夫,乌克兰)
ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table
Department of Chemical Engineering, Massachusetts Institute of Technology(麻省理工学院化学工程系);Center for Computational Science and Engineering, Massachusetts Institute of Technology(麻省理工学院计算科学与工程中心);Institute for Theoretical Chemistry, University of Stuttgart(斯图加特大学理论化学研究所);Institute for Artificial Intelligence, University of Stuttgart(斯图加特大学人工智能研究所);Department of Chemistry, Massachusetts Institute of Technology(麻省理工学院化学系)
Topology-Aware Multiscale Mixture of Experts for Efficient Molecular Property Prediction
School of Mathematics and Statistics(数学与统计学学院);Victoria University of Wellington(威灵顿维多利亚大学);School of Physical and Mathematical Sciences(物理与数学科学学院);Nanyang Technological University(南洋理工大学)