Task Assignment With Efficient Federated Preference Learning in Spatial Crowdsourcing

Miao, Hao; Zhong, Xiaolong; Liu, Jiaxin; Zhao, Yan; Zhao, Xiangyu; Qian, Weizhu; Zheng, Kai; Jensen, Christian S.

doi:10.1109/tkde.2023.3311816

Cited by 3 publications

(1 citation statement)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has greatly improved the MTS prediction performance (Yin and Shang 2016;Liu et al 2022Liu et al , 2021Zhou et al 2023a;Wang et al 2021;Zhou et al 2020b), leading to a proliferation of deep forecasting models (Wu et al 2021(Wu et al , 2019Shabani et al 2023; Figure 1: Comparison between Fixed Patch and Extendable Patch. Miao et al 2024Miao et al , 2023Huang et al 2023). From a technical perspective, extending one-dimensional time series to high-dimensional sequences through temporal patching can enhance the local semantics at each time step and provides significant advantages for subsequent dependency structure mining (Nie et al 2023;Zhang and Yan 2023).…”

Section: Introductionmentioning

confidence: 99%

HDMixer: Hierarchical Dependency with Extendable Patch for Multivariate Time Series Forecasting

Huang,

Shen,

Zhang

et al. 2024

AAAI

View full text Add to dashboard Cite

Multivariate time series (MTS) prediction has been widely adopted in various scenarios. Recently, some methods have employed patching to enhance local semantics and improve model performance. However, length-fixed patch are prone to losing temporal boundary information, such as complete peaks and periods. Moreover, existing methods mainly focus on modeling long-term dependencies across patches, while paying little attention to other dimensions (e.g., short-term dependencies within patches and complex interactions among cross-variavle patches). To address these challenges, we propose a pure MLP-based HDMixer, aiming to acquire patches with richer semantic information and efficiently modeling hierarchical interactions. Specifically, we design a Length-Extendable Patcher (LEP) tailored to MTS, which enriches the boundary information of patches and alleviates semantic incoherence in series. Subsequently, we devise a Hierarchical Dependency Explorer (HDE) based on pure MLPs. This explorer effectively models short-term dependencies within patches, long-term dependencies across patches, and complex interactions among variables. Extensive experiments on 9 real-world datasets demonstrate the superiority of our approach. The code is available at https://github.com/hqh0728/HDMixer.

show abstract