Search

Your search keyword '"Tang, Han"' showing total 1,305 results
Start Over Author "Tang, Han"
1,305 results on '"Tang, Han"'

1. Expert consensus on workflow of PET/CT with long axial field-of-view

Author

Liu, Guobing, Gu, Yushen, Sollini, Martina, Lazar, Alexandra, Besson, Florent L., Li, Sijin, Wu, Zhifang, Nardo, Lorenzo, Al-Ibraheem, Akram, Zheng, Jiefu, Kulkarni, Harshad R., Rominger, Axel, Fan, Wei, Zhu, Xiaohua, Zhao, Xinming, Wu, Hubing, Liu, Jianjun, Li, Biao, Cheng, Zhaoping, Wang, Ruimin, Xu, Baixuan, Agostini, Denis, Tang, Han, Tan, Lijie, Yang, Zhi, Huo, Li, Gu, Jianying, and Shi, Hongcheng

Published
2025
Full Text
View/download PDF

5. Contextual Molecule Representation Learning from Chemical Reaction Knowledge

Author

Tang, Han, Feng, Shikun, Lin, Bicheng, Ni, Yuyan, Liu, JIngjing, Ma, Wei-Ying, and Lan, Yanyan

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Quantitative Biology - Biomolecules
Abstract

In recent years, self-supervised learning has emerged as a powerful tool to harness abundant unlabelled data for representation learning and has been broadly adopted in diverse areas. However, when applied to molecular representation learning (MRL), prevailing techniques such as masked sub-unit reconstruction often fall short, due to the high degree of freedom in the possible combinations of atoms within molecules, which brings insurmountable complexity to the masking-reconstruction paradigm. To tackle this challenge, we introduce REMO, a self-supervised learning framework that takes advantage of well-defined atom-combination rules in common chemistry. Specifically, REMO pre-trains graph/Transformer encoders on 1.7 million known chemical reactions in the literature. We propose two pre-training objectives: Masked Reaction Centre Reconstruction (MRCR) and Reaction Centre Identification (RCI). REMO offers a novel solution to MRL by exploiting the underlying shared patterns in chemical reactions as \textit{context} for pre-training, which effectively infers meaningful representations of common chemistry knowledge. Such contextual representations can then be utilized to support diverse downstream molecular tasks with minimum finetuning, such as affinity prediction and drug-drug interaction prediction. Extensive experimental results on MoleculeACE, ACNet, drug-drug interaction (DDI), and reaction type classification show that across all tested downstream tasks, REMO outperforms the standard baseline of single-molecule masked modeling used in current MRL. Remarkably, REMO is the pioneering deep learning model surpassing fingerprint-based methods in activity cliff benchmarks., Comment: Preprint. Under Review

Published
2024

13. Masses of the conjectured H-dibaryon at different temperatures

Author

Wu, Liang-Kai, Tang, Han, Wang, Xin-Yang, and Li, Ning

Subjects
High Energy Physics - Lattice
Abstract

We present a lattice QCD determination of masses of the conjectured H-dibaryon $m_H$ at nine different temperatures $T/T_c =0.24, 0.63, 0.76, 0.84, 0.95, 1.09, 1.27, 1.52, 1.90$. In the meantime, the masses of baryon $N$, $\Sigma$, $\Xi$ and $\Lambda$ at different temperatures are also computed. The simulation is performed on anisotropic lattice with $N_f=2+1$ flavours of clover fermion at quark mass which corresponds to $m_\pi=384(4) {\rm MeV} $. The thermal ensembles were provided by the FASTSUM collaboration and the zero temperature ensembles by the Hadspec collaboration. We also calculate the spectral density of the correlation function of those particles. The spectral density distributions show rich peak structure at the lowest temperature, while at intermediate temperatures, the mass values of those particles obtained by extrapolation method reflect a two-peak structure. While the spectral density for octet baryon becomes smooth at $T/T_c = 1.27, 1.52, 1.90$, the spectral density for H-dibaryon becoms smooth at $T/T_c = 1.90$. At $T/T_c =0.24 $, the mass difference of H-dibaryon and $\Lambda$ pair $\Delta m = m_H - 2\,m_{\Lambda} $ is estimated to be $\Delta m = -14.6(6.2) {\rm MeV}$ which suggests there exists a bound H-dibaryon state., Comment: 12 pages,20 figures

Published
2023

17. Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs

Author

Kundu, Souvik, Sundaresan, Sairam, Sridhar, Sharath Nittur, Lu, Shunlin, Tang, Han, and Beerel, Peter A.

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Existing deep neural networks (DNNs) that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on either activation or weight conditioned convolution operations. However, such conditional learning costs additional multiply-accumulate (MAC) or addition operations, increasing inference memory and compute costs. To that end, we present a sparse mixture once for all adversarial training (SMART), that allows a model to train once and then in-situ trade-off between accuracy and robustness, that too at a reduced compute and parameter overhead. In particular, SMART develops two expert paths, for clean and adversarial images, respectively, that are then conditionally trained via respective dedicated sets of binary sparsity masks. Extensive evaluations on multiple image classification datasets across different models show SMART to have up to 2.72x fewer non-zero parameters costing proportional reduction in compute overhead, while yielding SOTA accuracy-robustness trade-off. Additionally, we present insightful observations in designing sparse masks to successfully condition on both clean and perturbed images., Comment: 5 pages, 5 figures, 2 tables

Published
2022

47. Engage your work, and enjoy your evening: How daily work engagement promotes non-work mastery and control experiences

Author

Li, Wei H., Zhou, Yang, Su, Jing X., Ma, Hong Y., Zhang, Jing, and Tang, Han Y.

Subjects
Influence, Research, Psychological research, Mastery learning -- Research, Control (Psychology) -- Research, Engagement (Philosophy) -- Influence
Abstract

Author(s): Wei H. Li [sup.1] [sup.2] , Yang Zhou [sup.1] , Jing X. Su [sup.1] , Hong Y. Ma [sup.1] , Jing Zhang [sup.1] , Han Y. Tang [sup.1] Author [...], The purpose of this study was to explore whether work engagement during the work period affected the specific recovery process during the non-work period. According to the Work-Home Resources (W-HR) model, this study from a day-level perspective used work engagement as a predictor of non-work mastery experiences as well as control experiences and explored whether the mediating role of recovery level at the end of the workday was established, which was beneficial to re-understand the role of work engagement in promoting employees' well-being in the transition from work to non-work. A daily diary design was adopted, with 2 measurement occasions per day for 1 workweek (N = 112 persons, 510 valid data sets in within-person level). Results about day-level relationships confirmed that work engagement was positively associated with the non-work mastery experiences as well as control experiences, recovery level at the end of the workday played a mediating role between daily work engagement and non-work control experiences, but the mediating role between work engagement and non-work mastery experiences was not established at the within-person level. Practical and theoretical implications for work engagement and non-work recovery were discussed.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results