Zobrazeno 1 - 10
of 114
pro vyhledávání: '"Mao, Wenji"'
Graph representation learning is a fundamental research issue in various domains of applications, of which the inductive learning problem is particularly challenging as it requires models to generalize to unseen graph structures during inference. In
Externí odkaz:
http://arxiv.org/abs/2403.17500
Autor:
Xiao, Xinglin, Wang, Yijie, Xu, Nan, Wang, Yuqi, Yang, Hanxuan, Wang, Minzheng, Luo, Yin, Wang, Lei, Mao, Wenji, Zeng, Daniel
The difficulty of the information extraction task lies in dealing with the task-specific label schemas and heterogeneous data structures. Recent work has proposed methods based on large language models to uniformly model different information extract
Externí odkaz:
http://arxiv.org/abs/2312.15548
Autor:
Luo, Yin, Kong, Qingchao, Xu, Nan, Cao, Jia, Hao, Bao, Qu, Baoyu, Chen, Bo, Zhu, Chao, Zhao, Chenyang, Zhang, Donglei, Feng, Fan, Zhao, Feifei, Sun, Hailong, Yang, Hanxuan, Pan, Haojun, Liu, Hongyu, Guo, Jianbin, Du, Jiangtao, Wang, Jingyi, Li, Junfeng, Sun, Lei, Liu, Liduo, Dong, Lifeng, Liu, Lili, Wang, Lin, Zhang, Liwen, Wang, Minzheng, Wang, Pin, Yu, Ping, Li, Qingxiao, Yan, Rui, Zou, Rui, Li, Ruiqun, Huang, Taiwen, Wang, Xiaodong, Wu, Xiaofei, Peng, Xin, Zhang, Xina, Fang, Xing, Xiao, Xinglin, Hao, Yanni, Dong, Yao, Wang, Yigang, Liu, Ying, Jiang, Yongyu, Wang, Yungan, Wang, Yuqi, Wang, Zhangsheng, Yu, Zhaoxin, Luo, Zhen, Mao, Wenji, Wang, Lei, Zeng, Dajun
As the latest advancements in natural language processing, large language models (LLMs) have achieved human-level language understanding and generation abilities in many real-world tasks, and even have been regarded as a potential path to the artific
Externí odkaz:
http://arxiv.org/abs/2312.14862
Graph representation learning is a fundamental research theme and can be generalized to benefit multiple downstream tasks from the node and link levels to the higher graph level. In practice, it is desirable to develop task-agnostic general graph rep
Externí odkaz:
http://arxiv.org/abs/2312.05519
Autor:
Zhao, Jiahao, Mao, Wenji
Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work argues th
Externí odkaz:
http://arxiv.org/abs/2210.14957
Graph representation learning is a fundamental research issue and benefits a wide range of applications on graph-structured data. Conventional artificial neural network-based methods such as graph neural networks (GNNs) and variational graph auto-enc
Externí odkaz:
http://arxiv.org/abs/2211.01952
Autor:
Zeng, Zhixiong, Mao, Wenji
Cross-Modal Retrieval (CMR) is an important research topic across multimodal computing and information retrieval, which takes one type of data as the query to retrieve relevant data of another type. It has been widely used in many real-world applicat
Externí odkaz:
http://arxiv.org/abs/2201.02772
The explosive increase of multimodal data makes a great demand in many cross-modal applications that follow the strict prior related assumption. Thus researchers study the definition of cross-modal correlation category and construct various classific
Externí odkaz:
http://arxiv.org/abs/2109.00693
Publikováno v:
Neurocomputing, 576 (2024) 127342
Graph representation learning is a fundamental problem for modeling relational data and benefits a number of downstream applications. Traditional Bayesian-based graph models and recent deep learning based GNN either suffer from impracticability or la
Externí odkaz:
http://arxiv.org/abs/2106.11721