2 code implementations • 22 Aug 2023 • Shengsheng Lin, Weiwei Lin, Wentai Wu, Feiyu Zhao, Ruichao Mo, Haotong Zhang
To address these issues, we propose two novel strategies to reduce the number of iterations in RNNs for LTSF tasks: Segment-wise Iterations and Parallel Multi-step Forecasting (PMF).
Ranked #1 on Time Series Forecasting on Weather (720)
no code implementations • 9 Aug 2023 • Shengsheng Lin, Weiwei Lin, Wentai Wu, SongBo Wang, Yongxiang Wang
Recently, the superiority of Transformer for long-term time series forecasting (LTSF) tasks has been challenged, particularly since recent work has shown that simple models can outperform numerous Transformer-based approaches.
no code implementations • 14 Sep 2021 • Wentai Wu, Ligang He, Weiwei Lin
Both classification and regression tasks are susceptible to the biased distribution of training data.
1 code implementation • 2 Feb 2021 • Wentai Wu, Ligang He, Weiwei Lin, Carsten Maple
The results show that the selective behaviour of our algorithm leads to a significant reduction in the number of communication rounds and the amount of time (up to 2. 4x speedup) for the global model to converge and also provides accuracy gain.
no code implementations • 3 Nov 2020 • Tiansheng Huang, Weiwei Lin, Wentai Wu, Ligang He, Keqin Li, Albert Y. Zomaya
The client selection policy is critical to an FL process in terms of training efficiency, the final model's quality as well as fairness.
no code implementations • 28 Jul 2020 • Wentai Wu, Ligang He, Weiwei Lin, Rui Mao
In this paper, a multi-layer federated learning protocol called HybridFL is designed for the MEC architecture.
no code implementations • 3 Oct 2019 • Wentai Wu, Ligang He, Weiwei Lin, Rui Mao, Carsten Maple, Stephen Jarvis
Federated learning (FL) has attracted increasing attention as a promising approach to driving a vast number of end devices with artificial intelligence.
no code implementations • 3 Aug 2019 • Wentai Wu, Ligang He, Weiwei Lin, Yi Su, Yuhua Cui, Carsten Maple, Stephen Jarvis
In light of this, we have developed a prediction-driven, unsupervised anomaly detection scheme, which adopts a backbone model combining the decomposition and the inference of time series data.