Xu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xu Zhang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Peng Wang
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China
6 shared publications - Wei Wang
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China
6 shared publications - Qitong Wang
Université Paris Cité, Paris, France
2 shared publications - Qitong Wang
Universite Paris Cite Paris France
2 shared publications - Chang Xu
Microsoft Research, China
1 shared publication - Chen Wang
Tsinghua University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 11 May 2026
- Published by MDPI AG in Preprints.org
A Survey on Data Generation for Time Series: Taxonomy, Review and Prospects
Time series generation (TSG) plays a fundamental role in data engineering and knowledge discovery, serving as a key enabler for data augmentation, representation learning, privacy preservation, and scenario simulation analysis in temporal data mining. By synthesizing realistic and controllable time series, TSG directly benefits downstream tasks such as forecasting, anomaly detection, and classification by data augmentation and improving model generalization. This survey presents a comprehensive and systematic review of TSG methodologies, spanning traditional non-deep learning approaches, such as rule-based, statistical, and simulation-based methods, and modern deep generative models, including variational autoencoders, generative adversarial networks, diffusion models, normalizing flows, and large language models. To organize the rapidly growing literature, we introduce a unified multi-level taxonomy to organize the technical landscape of TSG and clarify the relationships among diverse approaches. The taxonomy emphasizes underlying modeling principles rather than individual representative models. Specifically, it categorizes TSG methods according to modeling backbones, generation settings (conditional versus unconditional), sampling regularity, and modality characteristics. Building on this taxonomy, we systematically review advanced methods within each category and discuss how they address key challenges such as irregular sampling, long-sequence modeling, multivariate dependencies, and controllable generation, and how they are applied in real-world scenarios. Furthermore, we present a holistic evaluation framework encompassing five core dimensions, including fidelity, diversity, controllability, downstream performance, and privacy protection. Finally, we identify critical open challenges and outline promising research directions from data characteristics, application scenarios, and modeling paradigm perspectives. This survey aims to serve as a structured reference and roadmap for researchers and practitioners in this rapidly evolving field.
- 11 May 2026
- Published by MDPI AG in Preprints.org
Open AccessA Survey on Data Generation for Time Series: Taxonomy, Review and Prospects
Time series generation (TSG) plays a fundamental role in data engineering and knowledge discovery, serving as a key enabler for data augmentation, representation learning, privacy preservation, and scenario simulation analysis in temporal data mining. By synthesizing realistic and controllable time series, TSG directly benefits downstream tasks such as forecasting, anomaly detection, and classification by data augmentation and improving model generalization. This survey presents a comprehensive and systematic review of TSG methodologies, spanning traditional non-deep learning approaches, such as rule-based, statistical, and simulation-based methods, and modern deep generative models, including variational autoencoders, generative adversarial networks, diffusion models, normalizing flows, and large language models. To organize the rapidly growing literature, we introduce a unified multi-level taxonomy to organize the technical landscape of TSG and clarify the relationships among diverse approaches. The taxonomy emphasizes underlying modeling principles rather than individual representative models. Specifically, it categorizes TSG methods according to modeling backbones, generation settings (conditional versus unconditional), sampling regularity, and modality characteristics. Building on this taxonomy, we systematically review advanced methods within each category and discuss how they address key challenges such as irregular sampling, long-sequence modeling, multivariate dependencies, and controllable generation, and how they are applied in real-world scenarios. Furthermore, we present a holistic evaluation framework encompassing five core dimensions, including fidelity, diversity, controllability, downstream performance, and privacy protection. Finally, we identify critical open challenges and outline promising research directions from data characteristics, application scenarios, and modeling paradigm perspectives. This survey aims to serve as a structured reference and roadmap for researchers and practitioners in this rapidly evolving field.
- Open Access
A Lightweight Sparse Interaction Network for Time Series Forecasting
Recent work shows that linear models can outperform several transformer models in long-term time-series forecasting (TSF). However, instead of explicitly performing temporal interaction through self-attention, linear models implicitly perform it based on stacked MLP structures, which may be insufficient in capturing the complex temporal dependencies and their performance still has potential for improvement. To this end, we propose a Lightweight Sparse Interaction Network (LSINet) for TSF task. Inspired by the sparsity of self-attention, we propose a Multihead Sparse Interaction Mechanism (MSIM). Different from self-attention, MSIM learns the important connections between time steps through sparsity-induced Bernoulli distribution to capture temporal dependencies for TSF. The sparsity is ensured by the proposed self-adaptive regularization loss. Moreover, we observe the shareability of temporal interactions and propose to perform Shared Interaction Learning (SIL) for MSIM to further enhance efficiency and improve convergence. LSINet is a linear model comprising only MLP structures with low overhead and equipped with explicit temporal interaction mechanisms. Extensive experiments on public datasets show that LSINet achieves both higher accuracy and better efficiency than advanced linear models and transformer models in TSF tasks. The code is available at the link https://github.com/Meteor-Stars/LSINet.
Open AccessA Lightweight Sparse Interaction Network for Time Series Forecasting
Recent work shows that linear models can outperform several transformer models in long-term time-series forecasting (TSF). However, instead of explicitly performing temporal interaction through self-attention, linear models implicitly perform it based on stacked MLP structures, which may be insufficient in capturing the complex temporal dependencies and their performance still has potential for improvement. To this end, we propose a Lightweight Sparse Interaction Network (LSINet) for TSF task. Inspired by the sparsity of self-attention, we propose a Multihead Sparse Interaction Mechanism (MSIM). Different from self-attention, MSIM learns the important connections between time steps through sparsity-induced Bernoulli distribution to capture temporal dependencies for TSF. The sparsity is ensured by the proposed self-adaptive regularization loss. Moreover, we observe the shareability of temporal interactions and propose to perform Shared Interaction Learning (SIL) for MSIM to further enhance efficiency and improve convergence. LSINet is a linear model comprising only MLP structures with low overhead and equipped with explicit temporal interaction mechanisms. Extensive experiments on public datasets show that LSINet achieves both higher accuracy and better efficiency than advanced linear models and transformer models in TSF tasks. The code is available at the link https://github.com/Meteor-Stars/LSINet.
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2848-2859
Multi-period Learning for Financial Time Series Forecasting
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2848-2859
Open AccessMulti-period Learning for Financial Time Series Forecasting
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 611-620
Global Feature Enhancing and Fusion Framework for Strain Gauge Status Recognition
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 611-620
Open AccessGlobal Feature Enhancing and Fusion Framework for Strain Gauge Status Recognition
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (12) , 13304-13312
A Lightweight Sparse Interaction Network for Time Series Forecasting
Recent work shows that linear models can outperform several transformer models in long-term time-series forecasting (TSF). However, instead of explicitly performing temporal interaction through self-attention, linear models implicitly perform it based on stacked MLP structures, which may be insufficient in capturing the complex temporal dependencies and their performance still has potential for improvement. To this end, we propose a Lightweight Sparse Interaction Network (LSINet) for TSF task. Inspired by the sparsity of self-attention, we propose a Multihead Sparse Interaction Mechanism (MSIM). Different from self-attention, MSIM learns the important connections between time steps through sparsity-induced Bernoulli distribution to capture temporal dependencies for TSF. The sparsity is ensured by the proposed self-adaptive regularization loss. Moreover, we observe the shareability of temporal interactions and propose to perform Shared Interactions Learning (SIL) for MSIM to further enhance efficiency and improve convergence. LSINet is a linear model comprising only MLP structures with low overhead and equipped with explicit temporal interaction mechanisms. Extensive experiments on public datasets show that LSINet achieves both higher accuracy and better efficiency than advanced linear models and transformer models in TSF tasks.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (12) , 13304-13312
Open AccessA Lightweight Sparse Interaction Network for Time Series Forecasting
Recent work shows that linear models can outperform several transformer models in long-term time-series forecasting (TSF). However, instead of explicitly performing temporal interaction through self-attention, linear models implicitly perform it based on stacked MLP structures, which may be insufficient in capturing the complex temporal dependencies and their performance still has potential for improvement. To this end, we propose a Lightweight Sparse Interaction Network (LSINet) for TSF task. Inspired by the sparsity of self-attention, we propose a Multihead Sparse Interaction Mechanism (MSIM). Different from self-attention, MSIM learns the important connections between time steps through sparsity-induced Bernoulli distribution to capture temporal dependencies for TSF. The sparsity is ensured by the proposed self-adaptive regularization loss. Moreover, we observe the shareability of temporal interactions and propose to perform Shared Interactions Learning (SIL) for MSIM to further enhance efficiency and improve convergence. LSINet is a linear model comprising only MLP structures with low overhead and equipped with explicit temporal interaction mechanisms. Extensive experiments on public datasets show that LSINet achieves both higher accuracy and better efficiency than advanced linear models and transformer models in TSF tasks.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8595-8603
Enhancing Adaptive Deep Networks for Image Classification via Uncertainty-aware Decision Fusion
Handling varying computational resources is a critical issue in modern AI applications. Adaptive deep networks, featuring the dynamic employment of multiple classifier heads among different layers, have been proposed to address classification tasks under varying computing resources. Existing approaches typically utilize the last classifier supported by the available resources for inference, as they believe that the last classifier always performs better across all classes. However, our findings indicate that earlier classifier heads can outperform the last head for certain classes. Based on this observation, we introduce the Collaborative Decision Making (CDM) module, which fuses the multiple classifier heads to enhance the inference performance of adaptive deep networks. CDM incorporates an uncertainty-aware fusion method based on evidential deep learning (EDL), that utilizes the reliability (uncertainty values) from the first c-1 classifiers to improve the c-th classifier' accuracy. We also design a balance term that reduces fusion saturation and unfairness issues caused by EDL constraints to improve the fusion quality of CDM. Finally, a regularized training strategy that uses the last classifier to guide the learning process of early classifiers is proposed to further enhance the CDM module's effect, called the Guided Collaborative Decision Making (GCDM) framework. The experimental evaluation demonstrates the effectiveness of our approaches. Results on ImageNet datasets show CDM and GCDM obtain 0.4% to 2.8% accuracy improvement (under varying computing resources) on popular adaptive networks. The code is available at the link https://github.com/Meteor-Stars/GCDM_AdaptiveNet.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8595-8603
Open AccessEnhancing Adaptive Deep Networks for Image Classification via Uncertainty-aware Decision Fusion
Handling varying computational resources is a critical issue in modern AI applications. Adaptive deep networks, featuring the dynamic employment of multiple classifier heads among different layers, have been proposed to address classification tasks under varying computing resources. Existing approaches typically utilize the last classifier supported by the available resources for inference, as they believe that the last classifier always performs better across all classes. However, our findings indicate that earlier classifier heads can outperform the last head for certain classes. Based on this observation, we introduce the Collaborative Decision Making (CDM) module, which fuses the multiple classifier heads to enhance the inference performance of adaptive deep networks. CDM incorporates an uncertainty-aware fusion method based on evidential deep learning (EDL), that utilizes the reliability (uncertainty values) from the first c-1 classifiers to improve the c-th classifier' accuracy. We also design a balance term that reduces fusion saturation and unfairness issues caused by EDL constraints to improve the fusion quality of CDM. Finally, a regularized training strategy that uses the last classifier to guide the learning process of early classifiers is proposed to further enhance the CDM module's effect, called the Guided Collaborative Decision Making (GCDM) framework. The experimental evaluation demonstrates the effectiveness of our approaches. Results on ImageNet datasets show CDM and GCDM obtain 0.4% to 2.8% accuracy improvement (under varying computing resources) on popular adaptive networks. The code is available at the link https://github.com/Meteor-Stars/GCDM_AdaptiveNet.