Pretraining molecular representation models without labels is fundamental to various applications. Conventional methods mainly process 2D molecular graphs and focus solely …
D Brooks, O Schwander… - Advances in …, 2019 - proceedings.neurips.cc
Covariance matrices have attracted attention for machine learning applications due to their capacity to capture interesting structure in the data. The main challenge is that one needs to …
X Hua, Y Ono, L Peng, Y Xu - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Principal component analysis (PCA) is a commonly used pattern analysis method that maps high-dimensional data into a lower-dimensional space maximizing the data variance, that …
N Zubić, D Gehrig, M Gehrig… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Today, state-of-the-art deep neural networks that process events first convert them into dense, grid-like input representations before using an off-the-shelf network. However …
CY Chuang, S Jegelka… - … on Machine Learning, 2023 - proceedings.mlr.press
Optimal transport aligns samples across distributions by minimizing the transportation cost between them, eg, the geometric distances. Yet, it ignores coherence structure in the data …
XS Nguyen - Proceedings of the IEEE/CVF International …, 2021 - openaccess.thecvf.com
In this paper, we propose a novel method for representation and classification of two-person interactions from 3D skeleton sequences. The key idea of our approach is to use Gaussian …
This article presents an overview of robot learning and adaptive control applications that can benefit from a joint use of Riemannian geometry and probabilistic representations. The roles …
M Zhang, W Li, SS Yu, K Wen, C Zhou, P Shi - Energy, 2021 - Elsevier
Used batteries from electric vehicles (EVs) can be utilized as retired battery energy storage systems (RBESSs) at battery swapping and charging stations (BSCSs) to enhance their …
Y Jiang, X Chang, Y Liu, L Ding… - Advances in Neural …, 2023 - proceedings.neurips.cc
We develop an advanced approach for extending Gaussian Differential Privacy (GDP) to general Riemannian manifolds. The concept of GDP stands out as a prominent privacy …