Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Wang, Yangkun"'
Publikováno v:
EMNLP findings 2023
Despite remarkable advances that large language models have achieved in chatbots, maintaining a non-toxic user-AI interactive environment has become increasingly critical nowadays. However, previous efforts in toxicity detection have been mostly base
Externí odkaz:
http://arxiv.org/abs/2310.17389
Recent advances of incorporating layout information, typically bounding box coordinates, into pre-trained language models have achieved significant performance in entity recognition from document images. Using coordinates can easily model the absolut
Externí odkaz:
http://arxiv.org/abs/2305.14828
Autor:
Jin, Jiarui, Wang, Yangkun, Zhang, Weinan, Gan, Quan, Song, Xiang, Yu, Yong, Zhang, Zheng, Wipf, David
Graph Neural Networks (GNNs), originally proposed for node classification, have also motivated many recent works on edge prediction (a.k.a., link prediction). However, existing methods lack elaborate design regarding the distinctions between two task
Externí odkaz:
http://arxiv.org/abs/2212.12970
Autor:
Du, Kounianhua, Zhang, Weinan, Zhou, Ruiwen, Wang, Yangkun, Zhao, Xilong, Jin, Jiarui, Gan, Quan, Zhang, Zheng, Wipf, David
Prediction over tabular data is an essential and fundamental problem in many important downstream tasks. However, existing methods either take a data instance of the table independently as input or do not fully utilize the multi-rows features and lab
Externí odkaz:
http://arxiv.org/abs/2206.06587
It has been observed that graph neural networks (GNN) sometimes struggle to maintain a healthy balance between the efficient modeling long-range dependencies across nodes while avoiding unintended consequences such oversmoothed node representations o
Externí odkaz:
http://arxiv.org/abs/2111.06592
Autor:
Chen, Jiuhai, Mueller, Jonas, Ioannidis, Vassilis N., Adeshina, Soji, Wang, Yangkun, Goldstein, Tom, Wipf, David
For supervised learning with tabular data, decision tree ensembles produced via boosting techniques generally dominate real-world applications involving iid training/test sets. However for graph data where the iid assumption is violated due to struct
Externí odkaz:
http://arxiv.org/abs/2110.13413
Autor:
Wang, Yangkun, Jin, Jiarui, Zhang, Weinan, Yang, Yongyi, Chen, Jiuhai, Gan, Quan, Yu, Yong, Zhang, Zheng, Huang, Zengfeng, Wipf, David
Graph neural networks (GNNs) and label propagation represent two interrelated modeling strategies designed to exploit graph structure in tasks such as node property prediction. The former is typically based on stacked message-passing layers that shar
Externí odkaz:
http://arxiv.org/abs/2110.07190
Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs. However, in addition to their reliance on elaborate architectures and algorithm
Externí odkaz:
http://arxiv.org/abs/2103.13355
Autor:
Yang, Yongyi, Liu, Tang, Wang, Yangkun, Zhou, Jinjing, Gan, Quan, Wei, Zhewei, Zhang, Zheng, Huang, Zengfeng, Wipf, David
Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e.g., as can occur as a result of graph hetero
Externí odkaz:
http://arxiv.org/abs/2103.06064
Autor:
Zang, Yihao, Hu, Yan, Xu, Chenyu, Wu, Shenjie, Wang, Yangkun, Ning, Zhiyuan, Han, Zegang, Si, Zhanfeng, Shen, Weijuan, Zhang, Yayao, Fang, Lei, Zhang, TianZhen
Publikováno v:
In iScience 20 August 2021 24(8)
