Výsledky vyhledávání - "Liu, Qingxiang"

Report

Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting

Autor: Liu, Qingxiang, Liu, Xu, Liu, Chenghao, Wen, Qingsong, Liang, Yuxuan

Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential of langua

Externí odkaz: http://arxiv.org/abs/2405.14252

Zobrazit plný text záznamu

Report

Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach

Autor: Liu, Qingxiang, Sun, Sheng, Liang, Yuxuan, Xue, Jingjing, Liu, Min

The existing federated learning (FL) methods for spatio-temporal forecasting fail to capture the inherent spatio-temporal heterogeneity, which calls for personalized FL (PFL) methods to model the spatio-temporally variant patterns. While contrastive

Externí odkaz: http://arxiv.org/abs/2404.03702

Zobrazit plný text záznamu

Report

Online Spatio-Temporal Correlation-Based Federated Learning for Traffic Flow Forecasting

Autor: Liu, Qingxiang, Sun, Sheng, Liu, Min, Wang, Yuwei, Gao, Bo

Traffic flow forecasting (TFF) is of great importance to the construction of Intelligent Transportation Systems (ITS). To mitigate communication burden and tackle with the problem of privacy leakage aroused by centralized forecasting methods, Federat

Externí odkaz: http://arxiv.org/abs/2302.08658

Zobrazit plný text záznamu

Report

Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation

Autor: Wu, Zhiyuan, Sun, Sheng, Wang, Yuwei, Liu, Min, Pan, Quyang, Zhang, Junbo, Li, Zeju, Liu, Qingxiang

Federated learning (FL) is a privacy-preserving machine learning paradigm in which the server periodically aggregates local model parameters from clients without assembling their private data. Constrained communication and personalization requirement

Externí odkaz: http://arxiv.org/abs/2204.07028

Zobrazit plný text záznamu