Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learning

Kavli Affiliate: Feng Wang | First 5 Authors: Feng Wang, Senem Velipasalar, M. Cenk Gursoy, , | Summary: Federated learning (FL) aims at keeping client data local to preserve privacy. Instead of gathering the data itself, the server only collects aggregated gradient updates from clients. Following the popularity of FL, there has been considerable amount […]


Continue.. Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learning

Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction

Kavli Affiliate: Feng Wang | First 5 Authors: Feng Wang, Zilong Chen, Guokang Wang, Yafei Song, Huaping Liu | Summary: In this paper, we propose the Masked Space-Time Hash encoding (MSTH), a novel method for efficiently reconstructing dynamic 3D scenes from multi-view or monocular videos. Based on the observation that dynamic scenes often contain substantial […]


Continue.. Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction

Broadband CPW-based impedance-transformed Josephson parametric amplifier

Kavli Affiliate: Irfan Siddiqi | First 5 Authors: Bingcheng Qing, Long B. Nguyen, Xinyu Liu, Hengjiang Ren, William P. Livingston | Summary: Quantum-limited Josephson parametric amplifiers play a pivotal role in advancing the field of circuit quantum electrodynamics by enabling the fast and high-fidelity measurement of weak microwave signals. Therefore, it is necessary to develop […]


Continue.. Broadband CPW-based impedance-transformed Josephson parametric amplifier

DyExplainer: Explainable Dynamic Graph Neural Networks

Kavli Affiliate: Xiang Zhang | First 5 Authors: Tianchun Wang, Dongsheng Luo, Wei Cheng, Haifeng Chen, Xiang Zhang | Summary: Graph Neural Networks (GNNs) resurge as a trending research subject owing to their impressive ability to capture representations from graph-structured data. However, the black-box nature of GNNs presents a significant challenge in terms of comprehending […]


Continue.. DyExplainer: Explainable Dynamic Graph Neural Networks

Linear magneto-conductivity as a DC probe of time-reversal symmetry breaking

Kavli Affiliate: Joel E. Moore | First 5 Authors: Veronika Sunko, Chunxiao Liu, Marc Vila, Ilyoun Na, Yuchen Tang | Summary: Several optical experiments have shown that in magnetic materials the principal axes of response tensors can rotate in a magnetic field. Here we offer a microscopic explanation of this effect, and propose a closely […]


Continue.. Linear magneto-conductivity as a DC probe of time-reversal symmetry breaking

An Unconditionally Stable Iterative Decoupled Algorithm for Multiple-Network Poroelasticity Model

Kavli Affiliate: Feng Wang | First 5 Authors: Meng Lei, Mingchao Cai, Feng Wang, , | Summary: In this work, we introduce an iterative decoupled algorithm designed for addressing the quasi-static multiple-network poroelasticity problem. This problem pertains to the simultaneous modeling of fluid flow and deformations within an elastic porous medium permeated by multiple fluid […]


Continue.. An Unconditionally Stable Iterative Decoupled Algorithm for Multiple-Network Poroelasticity Model

Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

Kavli Affiliate: Xiang Zhang | First 5 Authors: Yihe Wang, Yu Han, Haishuai Wang, Xiang Zhang, | Summary: Contrastive representation learning is crucial in medical time series analysis as it alleviates dependency on labor-intensive, domain-specific, and scarce expert annotations. However, existing contrastive learning methods primarily focus on one single data level, which fails to fully […]


Continue.. Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

Kavli Affiliate: Xiang Zhang | First 5 Authors: Yihe Wang, Yu Han, Haishuai Wang, Xiang Zhang, | Summary: Contrastive representation learning is crucial in medical time series analysis as it alleviates dependency on labor-intensive, domain-specific, and scarce expert annotations. However, existing contrastive learning methods primarily focus on one single data level, which fails to fully […]


Continue.. Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

Kavli Affiliate: Xiang Zhang | First 5 Authors: Yihe Wang, Yu Han, Haishuai Wang, Xiang Zhang, | Summary: Contrastive representation learning is crucial in medical time series analysis as it alleviates dependency on labor-intensive, domain-specific, and scarce expert annotations. However, existing contrastive learning methods primarily focus on one single data level, which fails to fully […]


Continue.. Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series