Zobrazeno 1 - 10
of 105
pro vyhledávání: '"Chen, Xingyan"'
Autor:
Wei, Shaopeng, Egressy, Beni, Chen, Xingyan, Zhao, Yu, Zhuang, Fuzhen, Wattenhofer, Roger, Kou, Gang
Enterprise credit assessment is critical for evaluating financial risk, and Graph Neural Networks (GNNs), with their advanced capability to model inter-entity relationships, are a natural tool to get a deeper understanding of these financial networks
Externí odkaz:
http://arxiv.org/abs/2407.11615
Autor:
Chen, Xingyan, Du, Tian, Wang, Mu, Gu, Tiancheng, Zhao, Yu, Kou, Gang, Xu, Changqiao, Wu, Dapeng Oliver
Federated learning, as a promising distributed learning paradigm, enables collaborative training of a global model across multiple network edge clients without the need for central data collecting. However, the heterogeneity of edge data distribution
Externí odkaz:
http://arxiv.org/abs/2403.02360
Federated learning, a decentralized approach to machine learning, faces significant challenges such as extensive communication overheads, slow convergence, and unstable improvements. These challenges primarily stem from the gradient variance due to h
Externí odkaz:
http://arxiv.org/abs/2310.17200
Autor:
Wei, Shaopeng, Wang, Jun, Zhao, Yu, Chen, Xingyan, Li, Qing, Zhuang, Fuzhen, Liu, Ji, Ren, Fuji, Kou, Gang
Graph learning is a prevalent domain that endeavors to learn the intricate relationships among nodes and the topological structure of graphs. Over the years, graph learning has transcended from graph theory to graph data mining. With the advent of re
Externí odkaz:
http://arxiv.org/abs/2212.08966
Autor:
Guo, Yu, Xie, Zhilong, Chen, Xingyan, Chen, Huangen, Wang, Leilei, Du, Huaming, Wei, Shaopeng, Zhao, Yu, Li, Qing, Wu, Gang
Natural language understanding (NLU) has two core tasks: intent classification and slot filling. The success of pre-training language models resulted in a significant breakthrough in the two tasks. One of the promising solutions called BERT can joint
Externí odkaz:
http://arxiv.org/abs/2211.14829
Autor:
Zhao, Yu, Wei, Shaopeng, Guo, Yu, Yang, Qing, Chen, Xingyan, Li, Qing, Zhuang, Fuzhen, Liu, Ji, Kou, Gang
Publikováno v:
Information Sciences, 659(2024)1-17
Predicting the bankruptcy risk of small and medium-sized enterprises (SMEs) is an important step for financial institutions when making decisions about loans. Existing studies in both finance and AI research fields, however, tend to only consider eit
Externí odkaz:
http://arxiv.org/abs/2202.03874
Autor:
Zhao, Yu, Du, Huaming, Liu, Ying, Wei, Shaopeng, Chen, Xingyan, Zhuang, Fuzhen, Li, Qing, Liu, Ji, Kou, Gang
Stock Movement Prediction (SMP) aims at predicting listed companies' stock future price trend, which is a challenging task due to the volatile nature of financial markets. Recent financial studies show that the momentum spillover effect plays a signi
Externí odkaz:
http://arxiv.org/abs/2201.04965
Publikováno v:
Jixie chuandong, Vol 47, Pp 57-64 (2023)
At present, the demand for heavy-duty hydraulic automatic transmission in engineering machinery and other equipment is increasing. As one of the core components of such kind of transmission, the design of hydraulic torque converters requires better a
Externí odkaz:
https://doaj.org/article/f4a05c8ada1e4ba7b2f27dd71ffcd7ef
Autor:
Zhao, Yu, Wei, Shaopeng, Du, Huaming, Chen, Xingyan, Li, Qing, Zhuang, Fuzhen, Liu, Ji, Kou, Gang
Bi-type multi-relational heterogeneous graph (BMHG) is one of the most common graphs in practice, for example, academic networks, e-commerce user behavior graph and enterprise knowledge graph. It is a critical and challenge problem on how to learn th
Externí odkaz:
http://arxiv.org/abs/2112.13078
Autor:
Guo, Yu, Xie, Zhilong, Chen, Xingyan, Chen, Huangen, Wang, Leilei, Du, Huaming, Wei, Shaopeng, Zhao, Yu, Li, Qing, Wu, Gang
Publikováno v:
In Neurocomputing 28 July 2024 591