We propose a new fast method of measuring distances between large numbers of related high dimensional datasets called the Diffusion Earth Mover's Distance (EMD). We model the datasets as distributions supported on common data graph that is derived from the affinity matrix computed on the combined data. In such cases where the graph is a discretization of an underlying Riemannian closed manifold, we prove that Diffusion EMD is topologically equivalent to the standard EMD with a geodesic ground distance. Diffusion EMD can be computed in $\tilde{O}(n)$ time and is more accurate than similarly fast algorithms such as tree-based EMDs. We also show Diffusion EMD is fully differentiable, making it amenable to future uses in gradient-descent frameworks such as deep neural networks. Finally, we demonstrate an application of Diffusion EMD to single cell data collected from 210 COVID-19 patient samples at Yale New Haven Hospital. Here, Diffusion EMD can derive distances between patients on the manifold of cells at least two orders of magnitude faster than equally accurate methods. This distance matrix between patients can be embedded into a higher level patient manifold which uncovers structure and heterogeneity in patients. More generally, Diffusion EMD is applicable to all datasets that are massively collected in parallel in many medical and biological systems.
Differentiable Earth Mover's Distance for Data Compression at the High-Luminosity LHC
University of California at San Diego（加利福尼亚大学圣迭戈分校）；Fermi National Accelerator Laboratory（费米国家加速器实验室）；European Organization for Nuclear Research (CERN)（欧洲核子研究中心）
本文表明，一种流行的方法，监督嵌入文件的分类，即对比词移动器的嵌入，可以显着提高通过增加可解释性。这种可解释性是通过将聚类促进机制纳入对比损失来实现的。在几个公共数据集上，我们表明我们的方法在现有基线的基础上显着改进，同时通过识别一组最能代表特定类别的关键字来提供对集群的解释。我们的方法的动机部分是需要开发自然语言处理（NLP）方法的\textit{novel problem of assessing student work for scientific writing and thinking} -一个问题，是中央（教育）学习科学（LS）的领域。在这种情况下，我们表明，我们的方法导致一个有意义的评估学生的工作相关的实验室报告，从生物类，可以帮助LS研究人员深入了解学生的理解和评估科学思维过程的证据。
Surrogate-Assisted Framework for SI-Compliant Interconnect Design Optimization Using the Earth Mover's Distance
Information Processing Lab, TU Dortmund University（图腾大学信息处理实验室）；Pyramide2525/TU Dortmund University（图腾大学Pyramide2525分部）；EMC Technology Center Paderborn, Zuken GmbH（帕德博恩EMC技术中心，祖克纳公司）
Learning quantum data with the quantum Earth Mover's distance
Massachusetts Institute of Technology（麻省理工学院）；Scuola Normale Superiore（比萨高等师范学校）；University of Bologna（博洛尼亚大学）；University of New Mexico（新墨西哥大学）；Perimeter Institute for Theoretical Physics（圆周理论物理研究所）
Sparse Coding with Earth Mover's Distance for Multi-Instance Histogram Representation
National Digital Switching System Engineering & Technology Research Center（国家数字交换系统工程技术研究中心）；College of Computer and Information Engineering, Henan University of Economics and Law（河南财经政法大学计算机与信息工程学院）；University at Buffalo, The State University of New York（纽约州立大学布法罗分校）
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's Distance
Beijing Ultrapower Software Co.,Ltd.（北京超图软件股份有限公司）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Constructing Graph Node Embeddings via Discrimination of Similarity Distributions
Skolkovo Institute of Science and Technology (Skoltech)（斯科尔科沃科学技术研究所（斯科尔科沃理工学院））；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Institute for Information Transmission Problems of RAS（俄罗斯科学院信息传输问题研究所）
图中无监督学习节点嵌入问题是现代网络科学的重要研究方向之一。在这项工作中，我们提出了一个新的框架，这是旨在找到嵌入图中的节点之间的\textit{discriminating distributions of similarities (DDoS)}。通过最大化相似和不相似节点的解码相似性的分布之间的\textit{earth mover distance}来实现总体思想。由此产生的算法生成的嵌入，在现实世界的图中的链接预测的问题，这给一个国家的最先进的性能。
Multi-Modal Contrastive Learning for Implicit Earth Embeddings via Location Tying
Computational Methods Lab, HafenCity University Hamburg（汉堡港城大学计算方法实验室）；Dept. of Operations & Technology, Technical University of Munich（慕尼黑工业大学运营与技术系；海尔布隆数据科学中心；慕尼黑数据科学研究所）；Heilbronn Data Science Center（波恩大学大地测量与地理信息研究所）；Munich Data Science Institute；Institute of Geodesy and Geoinformation, University of Bonn
DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications
Laboratoire des Sciences du Climat et de l’Environnement, LSCE/IPSL, France；Department for AI in Society, Science；Technology, Zuse Institute Berlin, Germany；Department of Information Systems, University of Münster, Germany；Department of Computer Science, CNRS, INRIA \& École Normale Supérieure, Paris 75230, France
提出 DUNIA 方法，通过图像与全波形 LiDAR 跨模态对比对齐学习像素级嵌入，在零样本和微调设置下的多项地球观测环境监测任务中表现优于专门监督模型并接近或超越 SOTA。
Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings
School of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院）；School of Infrastructure Engineering, Dalian University of Technology（大连理工大学建设工程学院）；School of Information and Communication Engineering, Dalian University of Technology（大连理工大学信息与通信工程学院）；School of Software, Dalian University of Technology（大连理工大学软件学院）；School of Artificial Intelligence, Dalian University of Technology（大连理工大学人工智能学院）
What on Earth is AlphaEarth? Hierarchical structure and functional interpretability for global land cover
The Institute for Experiential Artificial Intelligence（体验式人工智能研究所）；Northeastern University（东北大学）；Gulf of Maine Research Institute（缅因湾研究机构）；School of Engineering and Architecture（工程与建筑学院）；Universidad Católica de Manizales（曼地拉天主教大学）；Grupo de Investigación en Recursos Hidrobiológicos（水资源生物学研究组）；Departamento de Ingeniería（工程系）；Universidad Nacional de Colombia（哥伦比亚国家大学）
