Neural controlled differential equations (NCDEs), which are continuous analogues to recurrent neural networks (RNNs), are a specialized model in (irregular) time-series processing. In comparison with similar models, e.g., neural ordinary differential equations (NODEs), the key distinctive characteristics of NCDEs are i) the adoption of the continuous path created by an interpolation algorithm from each raw discrete time-series sample and ii) the adoption of the Riemann--Stieltjes integral. It is the continuous path which makes NCDEs be analogues to continuous RNNs. However, NCDEs use existing interpolation algorithms to create the path, which is unclear whether they can create an optimal path. To this end, we present a method to generate another latent path (rather than relying on existing interpolation algorithms), which is identical to learning an appropriate interpolation method. We design an encoder-decoder module based on NCDEs and NODEs, and a special training method for it. Our method shows the best performance in both time-series classification and forecasting.
EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost
Graduate School of Artificial Intelligence, POSTECH, South Korea(人工智能研究生院,POSTECH,韩国);Department of Computer Science & Engineering, POSTECH, South Korea(计算机科学与工程系,POSTECH,韩国)
LAMP: Learnable Meta-Path Guided Adversarial Contrastive Learning for Heterogeneous Graphs
University of New South Wales(新南威尔士大学);Yonsei University(延世大学);RIKEN AIP(理化学研究所人工智能项目);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Radial Müntz-Szász Networks: Neural Architectures with Learnable Power Bases for Multidimensional Singularities
African Institute for Mathematical Sciences (AIMS), Research and Innovation Centre, Rwanda(非洲数学科学研究所(AIMS),研究与创新中心,卢旺达);Graduate School of Engineering, The University of Tokyo, Japan(东京大学工学研究科,日本);Axiom Research Group Department of Applied Mathematics and Computational Science, NM-AIST, Tanzania(Axiom研究组应用数学与计算科学系,NM-AIST,坦桑尼亚)
GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
Department of Data Science & AI, Monash University(墨尔本大学数据科学与人工智能系);Faculty of Medicine Dentistry and Health Sciences, University of Melbourne(墨尔本大学医学牙科与健康科学学院);Department of Computer Science, University College London(伦敦大学学院计算机科学系)
DiffSlack: Learning under Nonlinear Inequality Constraints via Learnable Slack Variables
State Key Laboratory of Tribology in Advanced Equipment, Tsinghua University(先进设备摩擦学国家重点实验室,清华大学);Beijing Key Laboratory of Transformative High-end Manufacturing Equipment and Technology, Department of Mechanical Engineering, Tsinghua University(transformative高端制造设备与技术北京市重点实验室,机械工程系,清华大学);Automotive Electronics Business Unit, Hirain Inc.(Hirain公司汽车电子事业部)
Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
Universität Potsdam(波茨坦大学);Freie Universität Berlin(柏林自由大学);Brandenburgische Technische Universität Cottbus-Senftenberg(勃兰登堡工业大学科特布斯-森夫滕贝格)
Heidelberg Institute for Theoretical Studies(海德堡理论研究所);Mathematical Institute, University of Oxford(牛津大学数学研究所);City University of Hong Kong(香港城市大学);IAR, Karlsruhe Institute of Technology(卡尔斯鲁厄技术大学IAR研究所);Department of Psychiatry, Warneford Hospital(沃内福德医院精神病科)