Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Meng, Ziqiao"'
Autor:
Wang, Haoyu, Ma, Guozheng, Meng, Ziqiao, Qin, Zeyu, Shen, Li, Zhang, Zhong, Wu, Bingzhe, Liu, Liu, Bian, Yatao, Xu, Tingyang, Wang, Xueqian, Zhao, Peilin
Self-alignment is an effective way to reduce the cost of human annotation while ensuring promising model capability. However, most current methods complete the data collection and training steps in a single round, which may overlook the continuously
Externí odkaz:
http://arxiv.org/abs/2402.07610
Reaction and retrosynthesis prediction are fundamental tasks in computational chemistry that have recently garnered attention from both the machine learning and drug discovery communities. Various deep learning approaches have been proposed to tackle
Externí odkaz:
http://arxiv.org/abs/2306.15890
Organic reaction prediction is a critical task in drug discovery. Recently, researchers have achieved non-autoregressive reaction prediction by modeling the redistribution of electrons, resulting in state-of-the-art top-1 accuracy, and enabling paral
Externí odkaz:
http://arxiv.org/abs/2306.06119
Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. The key to the GNNs is adopting the neural message-passing paradigm with two stages: aggregation and update. The cur
Externí odkaz:
http://arxiv.org/abs/2202.06281
Autor:
Chen, Yankai, Yang, Menglin, Zhang, Yingxue, Zhao, Mengchen, Meng, Ziqiao, Hao, Jianye, King, Irwin
Aiming to alleviate data sparsity and cold-start problems of traditional recommender systems, incorporating knowledge graphs (KGs) to supplement auxiliary information has recently gained considerable attention. Via unifying the KG with user-item inte
Externí odkaz:
http://arxiv.org/abs/2108.06468
Autor:
Liu, Hengkang, Gao, Jiawen, Feng, Mei, Cheng, Jinghui, Tang, Yuchen, Cao, Qi, Zhao, Ziji, Meng, Ziqiao, Zhang, Jiarui, Zhang, Guohong, Zhang, Chong, Zhao, Mingming, Yan, Yicen, Wang, Yang, Xue, Ruidong, Zhang, Ning, Li, Hang
Publikováno v:
In Cancer Cell 10 June 2024 42(6):1067-1085
Dynamic graphs arise in a plethora of practical scenarios such as social networks, communication networks, and financial transaction networks. Given a dynamic graph, it is fundamental and essential to learn a graph representation that is expected not
Externí odkaz:
http://arxiv.org/abs/2103.00164
A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types. Heterogeneous graph embedding is to embed rich structural and semantic information of a heterogeneous graph into low
Externí odkaz:
http://arxiv.org/abs/2002.01680