In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D shapes. Key to our construction is the introduction of a geometric distortion criterion, defined directly on the decoded shapes, translating the preservation of the metric on the decoding to the formation of linear paths in the underlying latent space. Our rationale lies in the observation that training samples alone are often insufficient to endow generative models with high fidelity, motivating the need for large training datasets. In contrast, metric preservation provides a rigorous way to control the amount of geometric distortion incurring in the construction of the latent space, leading in turn to synthetic samples of higher quality. We further demonstrate, for the first time, the adoption of differentiable intrinsic distances in the backpropagation of a geodesic loss. Our geometric priors are particularly relevant in the presence of scarce training data, where learning any meaningful latent structure can be especially challenging. The effectiveness and potential of our generative model is showcased in applications of style transfer, content generation, and shape completion.
RUM: network Representation learning throUgh Multi-level structural information preservation
Beijing Key Laboratory of Big Data Management and Analysis Methods（大数据管理与分析方法研究北京市重点实验室）；Renmin University of China（中国人民大学）；University of Electronic Science and Technology of China（电子科技大学）
近年来，我们见证了许多用于网络表示学习的技术的发现，从在随机游走中编码上下文到嵌入低阶连接，再到使用自动编码器寻找潜在空间表示。然而，现有的技术主要是在网络中的局部结构，而更高层次的属性，如全球社区结构往往被忽视。提出了一种新的网络表征学习模型框架RUM（Network表示学习throUgh Multi-level Structural Information Preservation）。在RUM中，我们将一个节点的三个基本方面，捕捉网络的特性在多个层面：一个节点的附属本地三合会，其邻里关系，其全球社区的联系。因此，该框架明确和全面地保留了网络的结构信息，将编码过程扩展到结构信息谱的局部端和全局端。该框架还具有足够的灵活性，可以采用各种社区发现算法作为其预处理器。实证结果表明，RUM学习的表示在现实生活中的任务表现出显着的性能优势。
Harmonized Multimodal Learning with Gaussian Process Latent Variable Models
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Noah’s Ark Lab（诺亚方舟实验室）；The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
PCRLv2: A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis
The University of Hong Kong（香港大学）；ShanghaiTech University（上海科技大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）
Latent Space Representation of Electricity Market Curves: Maintaining Structural Integrity
Kempelen Institute of Intelligent Technologies（智能技术研究所）；Department of Applied Mathematics and Statistics, Faculty of Mathematics, Physics and Informatics（应用数学与统计学系）；Comenius University（康门ius大学）
Dynamic Mixture of Latent Memories for Self-Evolving Agents
The Chinese University of Hong Kong（香港中文大学）；University of Oxford（牛津大学）；Nanyang Technological University（南洋理工大学）；University of Edinburgh（爱丁堡大学）；Shanghai Jiao Tong University（上海交通大学）
Platonic Projection Structures: Operator-Induced Observability in Representation Learning
Department of Applied Information Engineering, Faculty of Engineering, Suwa University of Science（诹访理工大学工程学院应用信息工程系）；Department of Information Engineering, Kanazawa Gakuin University（金泽学院大学信息工程系）
