Zobrazeno 81 - 90
of 746
pro vyhledávání: '"Chen, Huajun"'
Analogical reasoning is fundamental to human cognition and holds an important place in various fields. However, previous studies mainly focus on single-modal analogical reasoning and ignore taking advantage of structure knowledge. Notably, the resear
Externí odkaz:
http://arxiv.org/abs/2210.00312
Autor:
Deng, Shumin, Wang, Chengming, Li, Zhoubo, Zhang, Ningyu, Dai, Zelin, Chen, Hehong, Xiong, Feiyu, Yan, Ming, Chen, Qiang, Chen, Mosha, Chen, Jiaoyan, Pan, Jeff Z., Hooi, Bryan, Chen, Huajun
Business Knowledge Graphs (KGs) are important to many enterprises today, providing factual knowledge and structured data that steer many products and make them more intelligent. Despite their promising benefits, building business KG necessitates solv
Externí odkaz:
http://arxiv.org/abs/2209.15214
Answering complex queries over knowledge graphs (KG) is an important yet challenging task because of the KG incompleteness issue and cascading errors during reasoning. Recent query embedding (QE) approaches to embed the entities and relations in a KG
Externí odkaz:
http://arxiv.org/abs/2209.08779
Rule mining is an effective approach for reasoning over knowledge graph (KG). Existing works mainly concentrate on mining rules. However, there might be several rules that could be applied for reasoning for one relation, and how to select appropriate
Externí odkaz:
http://arxiv.org/abs/2209.05815
Autor:
Chen, Zhuo, Huang, Yufeng, Chen, Jiaoyan, Geng, Yuxia, Zhang, Wen, Fang, Yin, Pan, Jeff Z., Chen, Huajun
Zero-shot learning (ZSL) aims to predict unseen classes whose samples have never appeared during training. One of the most effective and widely used semantic information for zero-shot image classification are attributes which are annotations for clas
Externí odkaz:
http://arxiv.org/abs/2207.01328
Autor:
Geng, Yuxia, Chen, Jiaoyan, Zhang, Wen, Xu, Yajing, Chen, Zhuo, Pan, Jeff Z., Huang, Yufeng, Xiong, Feiyu, Chen, Huajun
Knowledge Graph (KG) and its variant of ontology have been widely used for knowledge representation, and have shown to be quite effective in augmenting Zero-shot Learning (ZSL). However, existing ZSL methods that utilize KGs all neglect the intrinsic
Externí odkaz:
http://arxiv.org/abs/2206.03739
Autor:
Chen, Xiang, Li, Lei, Zhang, Ningyu, Liang, Xiaozhuan, Deng, Shumin, Tan, Chuanqi, Huang, Fei, Si, Luo, Chen, Huajun
Prompt learning approaches have made waves in natural language processing by inducing better few-shot performance while they still follow a parametric-based learning paradigm; the oblivion and rote memorization problems in learning may encounter unst
Externí odkaz:
http://arxiv.org/abs/2205.14704
Existing data-centric methods for protein science generally cannot sufficiently capture and leverage biology knowledge, which may be crucial for many protein tasks. To facilitate research in this field, we create ProteinKG65, a knowledge graph for pr
Externí odkaz:
http://arxiv.org/abs/2207.10080
Autor:
Qu, Yincen, Zhang, Ningyu, Chen, Hui, Dai, Zelin, Xu, Zezhong, Wang, Chengming, Wang, Xiaoyu, Chen, Qiang, Chen, Huajun
In e-commerce, the salience of commonsense knowledge (CSK) is beneficial for widespread applications such as product search and recommendation. For example, when users search for ``running'' in e-commerce, they would like to find products highly rela
Externí odkaz:
http://arxiv.org/abs/2205.10843
Autor:
Chen, Mingyang, Zhang, Wen, Yao, Zhen, Chen, Xiangnan, Ding, Mengxiao, Huang, Fei, Chen, Huajun
We study the knowledge extrapolation problem to embed new components (i.e., entities and relations) that come with emerging knowledge graphs (KGs) in the federated setting. In this problem, a model trained on an existing KG needs to embed an emerging
Externí odkaz:
http://arxiv.org/abs/2205.04692