Zobrazeno 1 - 10
of 1 011
pro vyhledávání: '"Zhou, Zhengyang"'
Autor:
Zhao, Zhe, Wang, Pengkun, Wang, Xu, Wen, Haibin, Xie, Xiaolong, Zhou, Zhengyang, Zhang, Qingfu, Wang, Yang
Pre-training GNNs to extract transferable knowledge and apply it to downstream tasks has become the de facto standard of graph representation learning. Recent works focused on designing self-supervised pre-training tasks to extract useful and univers
Externí odkaz:
http://arxiv.org/abs/2404.14941
Trajectory modeling refers to characterizing human movement behavior, serving as a pivotal step in understanding mobility patterns. Nevertheless, existing studies typically ignore the confounding effects of geospatial context, leading to the acquisit
Externí odkaz:
http://arxiv.org/abs/2404.14073
Spatiotemporal learning plays a crucial role in mobile computing techniques to empower smart cites. While existing research has made great efforts to achieve accurate predictions on the overall dataset, they still neglect the significant performance
Externí odkaz:
http://arxiv.org/abs/2403.12391
Autor:
Zhou, Zhengyang, Huang, Qihe, Wang, Binwu, Hou, Jianpeng, Yang, Kuo, Liang, Yuxuan, Wang, Yang
Spatiotemporal (ST) learning has become a crucial technique to enable smart cities and sustainable urban development. Current ST learning models capture the heterogeneity via various spatial convolution and temporal evolution blocks. However, rapid u
Externí odkaz:
http://arxiv.org/abs/2403.01738
Enhancing accurate molecular property prediction relies on effective and proficient representation learning. It is crucial to incorporate diverse molecular relationships characterized by multi-similarity (self-similarity and relative similarities) be
Externí odkaz:
http://arxiv.org/abs/2401.17615
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community. Many recent studies have concentrated on meticulously reconciling various advantages, leading to designed mo
Externí odkaz:
http://arxiv.org/abs/2312.08403
Nuclear magnetic resonance (NMR) spectroscopy plays an essential role in deciphering molecular structure and dynamic behaviors. While AI-enhanced NMR prediction models hold promise, challenges still persist in tasks such as molecular retrieval, isome
Externí odkaz:
http://arxiv.org/abs/2311.13817
Autor:
Xia, Yutong, Liang, Yuxuan, Wen, Haomin, Liu, Xu, Wang, Kun, Zhou, Zhengyang, Zimmermann, Roger
Spatio-Temporal Graph (STG) forecasting is a fundamental task in many real-world applications. Spatio-Temporal Graph Neural Networks have emerged as the most popular method for STG forecasting, but they often struggle with temporal out-of-distributio
Externí odkaz:
http://arxiv.org/abs/2309.13378
Autor:
Wang, Yifei, Zhou, Zhengyang, Wang, Liqin, Laurentiev, John, Hou, Peter, Zhou, Li, Hong, Pengyu
When using machine learning (ML) to aid decision-making, it is critical to ensure that an algorithmic decision is fair, i.e., it does not discriminate against specific individuals/groups, particularly those from underprivileged populations. Existing
Externí odkaz:
http://arxiv.org/abs/2305.18160
Autor:
Wang, Dong, Huang, Wen-Xi, Zhou, Bo, Yu, Wenduo, Cao, Pei-Chao, Peng, Yu-Gui, Zhou, Zhengyang, Chen, Hongsheng, Zhu, Xue-Feng, Li, Ying
The eigenvalue of a non-Hermitian Hamiltonian often forms a self-intersecting Riemann surface, leading to a unique mode conversion phenomenon when the Hamiltonian evolves along certain loop paths around an exceptional point (EP). However, two fundame
Externí odkaz:
http://arxiv.org/abs/2304.12912