Výsledky vyhledávání - "Yang, Donghua"

Report

An Unsupervised Learning Framework Combined with Heuristics for the Maximum Minimal Cut Problem

Autor: Liu, Huaiyuan, Liu, Xianzhang, Yang, Donghua, Wang, Hongzhi, Long, Yingchi, Ji, Mengtong, Miao, Dongjing, Liang, Zhiyu

The Maximum Minimal Cut Problem (MMCP), a NP-hard combinatorial optimization (CO) problem, has not received much attention due to the demanding and challenging bi-connectivity constraint. Moreover, as a CO problem, it is also a daunting task for mach

Externí odkaz: http://arxiv.org/abs/2408.08484

Zobrazit plný text záznamu

Report

Unsupervised Multi-modal Feature Alignment for Time Series Representation Learning

Autor: Liang, Chen, Yang, Donghua, Liang, Zhiyu, Wang, Hongzhi, Liang, Zheng, Zhang, Xiyang, Huang, Jianfeng

In recent times, the field of unsupervised representation learning (URL) for time series data has garnered significant interest due to its remarkable adaptability across diverse downstream applications. Unsupervised learning goals differ from downstr

Externí odkaz: http://arxiv.org/abs/2312.05698

Zobrazit plný text záznamu

Report

Testing Higher-order Clusterability on graphs

Autor: Li, Yifei, Yang, Donghua, Li, Jianzhong

Analysis of higher-order organizations, usually small connected subgraphs called motifs, is a fundamental task on complex networks. This paper studies a new problem of testing higher-order clusterability: given query access to an undirected graph, ca

Externí odkaz: http://arxiv.org/abs/2310.04018

Zobrazit plný text záznamu

Report

Duet: efficient and scalable hybriD neUral rElation undersTanding

Autor: Zhang, Kaixin, Wang, Hongzhi, Lu, Yabin, Li, Ziqi, Shu, Chang, Yan, Yu, Yang, Donghua

Learned cardinality estimation methods have achieved high precision compared to traditional methods. Among learned methods, query-driven approaches have faced the workload drift problem for a long time. Although both data-driven and hybrid methods ar

Externí odkaz: http://arxiv.org/abs/2307.13494

Zobrazit plný text záznamu

Report

TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classification

Autor: Liu, Huaiyuan, Liu, Xianzhang, Yang, Donghua, Liang, Zhiyu, Wang, Hongzhi, Cui, Yong, Gu, Jun

Publikováno v: Information Sciences, 2024: 120914

Multivariate time series classification (MTSC) is an important data mining task, which can be effectively solved by popular deep learning technology. Unfortunately, the existing deep learning-based methods neglect the hidden dependencies in different

Externí odkaz: http://arxiv.org/abs/2304.05078

Zobrazit plný text záznamu