Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem. While many approaches have been proposed to solve this problem, they only utilize source data during training but do not take advantage of the fact that a single target example is available at the time of inference. Motivated by this, we propose a method that effectively uses the target sample during inference beyond mere classification. Our method has three components - (i) A label-preserving feature or metric transformation on source data such that the source samples are clustered in accordance with their class irrespective of their domain (ii) A generative model trained on the these features (iii) A label-preserving projection of the target point on the source-feature manifold during inference via solving an optimization problem on the input space of the generative model using the learned metric. Finally, the projected target is used in the classifier. Since the projected target feature comes from the source manifold and has the same label as the real target by design, the classifier is expected to perform better on it than the true target. We demonstrate that our method outperforms the state-of-the-art Domain Generalization methods on multiple datasets and tasks.
Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation
Department of Computer Science, Durham University（达勒姆大学计算机科学系）
异构领域自适应（HDA）解决了迁移学习问题，其中来自源和目标领域的数据具有不同的模态（例如，文本和图像）或特征尺寸（例如，用不同方法提取的特征）。这对于多模态数据分析是有用的。传统的领域自适应算法假设源样本和目标样本的表示位于同一特征空间，因此很可能无法解决异构领域自适应问题。当代国家的最先进的HDA方法通常是由复杂的优化目标的有利的性能，因此是计算昂贵的和较难推广。为了解决这些问题，我们提出了一种新的跨域结构保持投影（CDSPP）算法的HDA。作为经典LPP到异构域的扩展，CDSPP旨在学习特定于域的投影，将源域和目标域的样本特征映射到公共子空间，从而保持类一致性并充分对齐数据分布。CDSPP是简单的，并通过求解广义特征值问题具有确定性的解决方案。它自然适用于监督HDA，但也已扩展为半监督HDA，其中未标记的目标域样本可用。在HDA的常用基准数据集（即NIC-Caltech，Multilingual Reuters Collection，NUS-WIDE-ImageNet）上进行了广泛的实验，以及我们首次为HDA引入的NIC-Home数据集，因为它的类数量明显多于现有的数据集（65 vs 10，6和8）。监督和半监督HDA的实验结果表明，我们提出的方法对当代国家的最先进的方法的优越性能。
Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林技术大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Centre of eXplainable Artificial Intelligence, Technological University Dublin（可解释人工智能中心，都柏林技术大学）
Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels
Jiangsu University（江苏大学）；Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications（江苏省大数据泛在感知与智慧农业应用工程研究中心）；MIIT Key Laboratory of Pattern Analysis and Machine Intelligence（工信部模式分析与机器智能重点实验室）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
ProtoSSL: Self-Supervised Pretraining and Downstream Transfer for Projection-Based Prototype Models
Department of Computer Science（计算机科学系）；Center for Translational Data Science（转化数据科学中心）；Medical Scientist Training Program（医学科学家培训计划）；Pritzker School of Medicine（皮尔兹克医学院）；Center for Computational Medicine & Clinical AI（计算医学与临床人工智能中心）；Section of Biomedical Data Science, Department of Medicine（医学部生物医学数据科学部门）
Consistent Projection of Langevin Dynamics: Preserving Thermodynamics and Kinetics in Coarse-Grained Models
Max-Planck-Institute for Dynamics of Complex Technical Systems（复杂技术系统动力学马克斯-普朗克研究所）；Institute of Mathematics（数学研究所）；Brandenburgische Technische Universität Cottbus-Senftenberg（克托夫-森滕堡技术大学）；Department of Computer Science and Engineering（计算机科学与工程系）；Chalmers University of Technology（挑战大学）；University of Gothenburg（哥德堡大学）
Anti-drift in electronic nose via dimensionality reduction: a discriminative subspace projection approach
School of Computing, National University of Singapore（新加坡国立大学计算机学院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
School of Intelligence Science and Technology, Nanjing University, Suzhou, China（智能科学与技术学院，南京大学，苏州，中国）；School of Artificial Intelligence, Jilin University, China（人工智能学院，吉林大学，中国）
Ocean University of China（中国海洋大学）；State Key Laboratory of Integrated Services Networks (Xidian University)（综合业务网理论及关键技术国家重点实验室（西安电子科技大学））；Southeast University（东南大学）；Purple Mountain Laboratories（紫金山实验室）
Data Obfuscation through Latent Space Projection (LSP) for Privacy-Preserving AI Governance: Case Studies in Medical Diagnosis and Finance Fraud Detection
Preserving Task-Relevant Information Under Linear Concept Removal
University of Amsterdam, Department of Quantitative Economics（阿姆斯特丹大学量化经济学系）；New York University, Center for Data Science（纽约大学数据科学中心）；Tinbergen Institute（廷伯根研究所）
FedRAW: Preserving Rare-Label Influence in Asynchronous Federated Learning
School of Artificial Intelligence and Data Science, Indian Institute of Technology Jodhpur（印度焦特布尔印度理工学院人工智能与数据科学学院）；Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur（印度焦特布尔印度理工学院计算机科学与工程系）；Laboratoire d’Informatique de Grenoble (LIG), University of Grenoble Alpes（格勒诺布尔阿尔卑斯大学格勒诺布尔计算机实验室）
Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；School of Computer Science, Fudan University（复旦大学计算机科学技术学院）
Semi-Automatic Data Annotation guided by Feature Space Projection
Institute of Computing, University of Campinas（坎皮纳斯大学计算研究所）；Department of Information and Computing Sciences, Faculty of Science, Utrecht University（乌得勒支大学理学院信息与计算科学系）
Exploiting random projections and sparsity with random forests and gradient boosting methods -- Application to multi-label and multi-output learning, random forest model compression and leveraging input sparsity
University of Liège（列日大学）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）；Katholieke Universiteit Leuven（鲁汶天主教大学）
