Zobrazeno 1 - 10
of 876
pro vyhledávání: '"Zhou, Chenghu"'
Missing values are prevalent in multivariate time series, compromising the integrity of analyses and degrading the performance of downstream tasks. Consequently, research has focused on multivariate time series imputation, aiming to accurately impute
Externí odkaz:
http://arxiv.org/abs/2408.05740
The explosive growth of data fuels data-driven research, facilitating progress across diverse domains. The FAIR principles emerge as a guiding standard, aiming to enhance the findability, accessibility, interoperability, and reusability of data. Howe
Externí odkaz:
http://arxiv.org/abs/2408.04673
In Constrained Reinforcement Learning (CRL), agents explore the environment to learn the optimal policy while satisfying constraints. The penalty function method has recently been studied as an effective approach for handling constraints, which impos
Externí odkaz:
http://arxiv.org/abs/2407.15537
Autor:
Zhou, Jianping, Lu, Bin, Liu, Zhanyu, Pan, Siyu, Feng, Xuejun, Wei, Hua, Zheng, Guanjie, Wang, Xinbing, Zhou, Chenghu
Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missing values to facilitate data analysis and decision-making for Intellige
Externí odkaz:
http://arxiv.org/abs/2406.03511
Recent vision-language pre-trained models (VL-PTMs) have shown remarkable success in open-vocabulary tasks. However, downstream use cases often involve further fine-tuning of VL-PTMs, which may distort their general knowledge and impair their ability
Externí odkaz:
http://arxiv.org/abs/2405.16417
Autor:
Lu, Bin, Zhao, Ze, Han, Luyu, Gan, Xiaoying, Zhou, Yuntao, Zhou, Lei, Fu, Luoyi, Wang, Xinbing, Zhou, Chenghu, Zhang, Jing
Accurately reconstructing the global ocean deoxygenation over a century is crucial for assessing and protecting marine ecosystem. Existing expert-dominated numerical simulations fail to catch up with the dynamic variation caused by global warming and
Externí odkaz:
http://arxiv.org/abs/2405.07233
Autor:
Sheng, Shuqian, Xu, Yi, Zhang, Tianhang, Shen, Zanwei, Fu, Luoyi, Ding, Jiaxin, Zhou, Lei, Wang, Xinbing, Zhou, Chenghu
Automatic evaluation metrics for generated texts play an important role in the NLG field, especially with the rapid growth of LLMs. However, existing metrics are often limited to specific scenarios, making it challenging to meet the evaluation requir
Externí odkaz:
http://arxiv.org/abs/2404.19563
In this paper, we propose a multi-view visualization technology for spatio-temporal knowledge graph(STKG), which utilizes three distinct perspectives: knowledge tree, knowledge net, and knowledge map, to facilitate a comprehensive analysis of the STK
Externí odkaz:
http://arxiv.org/abs/2405.03697
Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations. However, the fundamental problem of understanding and analyzing how graph topology
Externí odkaz:
http://arxiv.org/abs/2404.07493
Autor:
Lu, Bin, Ma, Tingyan, Gan, Xiaoying, Wang, Xinbing, Zhu, Yunqiang, Zhou, Chenghu, Liang, Shiyu
Graph Neural Networks (GNNs) are widely deployed in vast fields, but they often struggle to maintain accurate representations as graphs evolve. We theoretically establish a lower bound, proving that under mild conditions, representation distortion in
Externí odkaz:
http://arxiv.org/abs/2404.04969