Zobrazeno 1 - 10
of 1 799
pro vyhledávání: '"Liang, Ke"'
Chain of thought finetuning (cot-finetuning) aims to endow small language models (SLM) with reasoning ability to improve their performance towards specific tasks by allowing them to imitate the reasoning procedure of large language models (LLM) beyon
Externí odkaz:
http://arxiv.org/abs/2404.09170
Using natural language processing (NLP) technologies to develop medical chatbots makes the diagnosis of the patient more convenient and efficient, which is a typical application in healthcare AI. Because of its importance, lots of research have been
Externí odkaz:
http://arxiv.org/abs/2312.02496
In recent years, the field of single-cell data analysis has seen a marked advancement in the development of clustering methods. Despite advancements, most of these algorithms still concentrate on analyzing the provided single-cell matrix data. Howeve
Externí odkaz:
http://arxiv.org/abs/2311.17104
Multi-view clustering thrives in applications where views are collected in advance by extracting consistent and complementary information among views. However, it overlooks scenarios where data views are collected sequentially, i.e., real-time data.
Externí odkaz:
http://arxiv.org/abs/2309.15135
Autor:
Liu, Meng, Liang, Ke, Hu, Dayu, Yu, Hao, Liu, Yue, Meng, Lingyuan, Tu, Wenxuan, Zhou, Sihang, Liu, Xinwang
Audiovisual data is everywhere in this digital age, which raises higher requirements for the deep learning models developed on them. To well handle the information of the multi-modal data is the key to a better audiovisual modal. We observe that thes
Externí odkaz:
http://arxiv.org/abs/2309.11845
Autor:
Wen, Yi, Liu, Suyuan, Wan, Xinhang, Wang, Siwei, Liang, Ke, Liu, Xinwang, Yang, Xihong, Zhang, Pei
Anchor-based multi-view graph clustering (AMVGC) has received abundant attention owing to its high efficiency and the capability to capture complementary structural information across multiple views. Intuitively, a high-quality anchor graph plays an
Externí odkaz:
http://arxiv.org/abs/2309.00024
Autor:
Wen, Yi, Wang, Siwei, Liang, Ke, Liang, Weixuan, Wan, Xinhang, Liu, Xinwang, Liu, Suyuan, Liu, Jiyuan, Zhu, En
The success of existing multi-view clustering (MVC) relies on the assumption that all views are complete. However, samples are usually partially available due to data corruption or sensor malfunction, which raises the research of incomplete multi-vie
Externí odkaz:
http://arxiv.org/abs/2308.16541
Autor:
Yang, Xihong, Jin, Jiaqi, Wang, Siwei, Liang, Ke, Liu, Yue, Wen, Yi, Liu, Suyuan, Zhou, Sihang, Liu, Xinwang, Zhu, En
Benefiting from the strong view-consistent information mining capacity, multi-view contrastive clustering has attracted plenty of attention in recent years. However, we observe the following drawback, which limits the clustering performance from furt
Externí odkaz:
http://arxiv.org/abs/2308.09000
Autor:
Yang, Xihong, Tan, Cheng, Liu, Yue, Liang, Ke, Wang, Siwei, Zhou, Sihang, Xia, Jun, Li, Stan Z., Liu, Xinwang, Zhu, En
Contrastive graph node clustering via learnable data augmentation is a hot research spot in the field of unsupervised graph learning. The existing methods learn the sampling distribution of a pre-defined augmentation to generate data-driven augmentat
Externí odkaz:
http://arxiv.org/abs/2308.08963
Autor:
Liu, Yue, Liang, Ke, Xia, Jun, Yang, Xihong, Zhou, Sihang, Liu, Meng, Liu, Xinwang, Li, Stan Z.
Deep graph clustering, which aims to group nodes into disjoint clusters by neural networks in an unsupervised manner, has attracted great attention in recent years. Although the performance has been largely improved, the excellent performance of the
Externí odkaz:
http://arxiv.org/abs/2308.06827