Fuxin Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Fuxin Jiang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Angjun Tang
School of Public Policy and Administration, Xi’an Jiaotong University, Xi’an, People’s Republic of China
2 shared publications- Ning Ma
School of Public Policy and Administration, Xi’an Jiaotong University, Xi’an 710049, China
2 shared publications - Tieying Zhang
Bytedance, San Jose, USA
2 shared publications - Xiaofeng Gao
Shanghai Jiao Tong University
2 shared publications - Xiuqi Huang
Zhejiang University, Hangzhou, China
2 shared publications - Yang Luo
MoE Key Lab of Artificial Intelligence, Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China
2 shared publications
Latest Publications
- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (5) , 3277-3290
Uncertainty-Aware Online Time Series Multi-Step Forecasting Framework in Cloud Systems
Accurate resource planning in large-scale systems relies on reliable predictions of future workloads, a task inherently challenged by their variability and dynamism. Previous prediction methods are either ineffective to deal with the changing dynamics of the series, or are highly black-boxed and unable to conduct effective theoretical analysis. To address these issues, we design an effective ensemble framework, Interval Prediction with Online Chasing (IPOC), tailored for multi-step interval forecasting in real-time systems. Theoretically, by formulating the task as a Dynamic Deterministic Markov Decision Process (Dd-MDP), an advanced theoretical framework is introduced to analyze problem solvability and derive conditions for the existence of feasible solutions. Incorporating the proposed Adaptive Copula Conformal Inference (ACCI) module and a well-designed Chasing Oracle, IPOC captures the changing dynamics and temporal dependencies to enable multi-step forecasting. We organically integrate advanced online learning theories with time series forecasting tasks to construct a forecasting framework that is both theoretically rigorous and practically effective. Theoretical analysis underpins IPOC’s effectiveness, demonstrating sublinear regret and adherence to confidence interval specifications. The chasing regret of the Chasing Oracle is$O(L_{c})$ , and the overall regret of IPOC is$O(\sqrt{L_{c} T \log |\mathcal {F}|})$ . Empirically, IPOC is validated through extensive experiments on five real-world datasets, including public datasets and different types of workload collected from Bytedance Cloud, with comparisons to 25 baselines and 4 forecasting horizons (1/5/10/30). Specifically, IPOC achieves an average reduction of over 20% in RMSE/MAE/SMAPE/$\rho$ -risk compared to baselines across five datasets. Besides, we apply our model to a case study on predictive auto-scaling tasks in actual large-scale cloud systems to validate its utility.- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (5) , 3277-3290
Uncertainty-Aware Online Time Series Multi-Step Forecasting Framework in Cloud Systems
Accurate resource planning in large-scale systems relies on reliable predictions of future workloads, a task inherently challenged by their variability and dynamism. Previous prediction methods are either ineffective to deal with the changing dynamics of the series, or are highly black-boxed and unable to conduct effective theoretical analysis. To address these issues, we design an effective ensemble framework, Interval Prediction with Online Chasing (IPOC), tailored for multi-step interval forecasting in real-time systems. Theoretically, by formulating the task as a Dynamic Deterministic Markov Decision Process (Dd-MDP), an advanced theoretical framework is introduced to analyze problem solvability and derive conditions for the existence of feasible solutions. Incorporating the proposed Adaptive Copula Conformal Inference (ACCI) module and a well-designed Chasing Oracle, IPOC captures the changing dynamics and temporal dependencies to enable multi-step forecasting. We organically integrate advanced online learning theories with time series forecasting tasks to construct a forecasting framework that is both theoretically rigorous and practically effective. Theoretical analysis underpins IPOC’s effectiveness, demonstrating sublinear regret and adherence to confidence interval specifications. The chasing regret of the Chasing Oracle is$O(L_{c})$ , and the overall regret of IPOC is$O(\sqrt{L_{c} T \log |\mathcal {F}|})$ . Empirically, IPOC is validated through extensive experiments on five real-world datasets, including public datasets and different types of workload collected from Bytedance Cloud, with comparisons to 25 baselines and 4 forecasting horizons (1/5/10/30). Specifically, IPOC achieves an average reduction of over 20% in RMSE/MAE/SMAPE/$\rho$ -risk compared to baselines across five datasets. Besides, we apply our model to a case study on predictive auto-scaling tasks in actual large-scale cloud systems to validate its utility.- 2 February 2026
- Published by Springer Nature in Operational Research
- Vol. 26 (2) , 28
Column generation-based diving heuristic and segmentation approach for the micro-service allocation problem with affinity in cloud computing
- 2 February 2026
- Published by Springer Nature in Operational Research
- Vol. 26 (2) , 28
Column generation-based diving heuristic and segmentation approach for the micro-service allocation problem with affinity in cloud computing
- Open Access
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 471-484
ABase: the Multi-Tenant NoSQL Serverless Database for Diverse and Dynamic Workloads in Large-scale Cloud Environments
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 471-484
Open AccessABase: the Multi-Tenant NoSQL Serverless Database for Diverse and Dynamic Workloads in Large-scale Cloud Environments
- 20 February 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 273
A deep multi-agent reinforcement learning approach for the micro-service migration problem with affinity in the cloud
- 20 February 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 273
A deep multi-agent reinforcement learning approach for the micro-service migration problem with affinity in the cloud
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 202-212
IPOC: An Adaptive Interval Prediction Model based on Online Chasing and Conformal Inference for Large-Scale Systems
In large-scale systems, due to system complexity and demand volatility, diverse and dynamic workloads make accurate predictions difficult. In this work, we address an online interval prediction problem (OnPred-Int) and adopt ensemble learning to solve it. We depict that the ensemble learning for OnPred-Int is a dynamic deterministic Markov Decision Process (Dd-MDP) and convert it into a stateful online learning task. Then we propose IPOC, a lightweight and flexible model able to produce effective confidence intervals, adapting the dynamics of real-time workload streams. At each time, IPOC selects a target model and executes chasing for it by a designed chasing oracle, during which process IPOC produces accurate confidence intervals. The effectiveness of IPOCis theoretically validated through sublinear regret analysis and satisfaction of confidence interval requirements. Besides, we conduct extensive experiments on 4 real-world datasets comparing with 19 baselines. To the best of our knowledge, we are the first to apply the frontier theory of online learning to time series prediction tasks.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 202-212
Open AccessIPOC: An Adaptive Interval Prediction Model based on Online Chasing and Conformal Inference for Large-Scale Systems
In large-scale systems, due to system complexity and demand volatility, diverse and dynamic workloads make accurate predictions difficult. In this work, we address an online interval prediction problem (OnPred-Int) and adopt ensemble learning to solve it. We depict that the ensemble learning for OnPred-Int is a dynamic deterministic Markov Decision Process (Dd-MDP) and convert it into a stateful online learning task. Then we propose IPOC, a lightweight and flexible model able to produce effective confidence intervals, adapting the dynamics of real-time workload streams. At each time, IPOC selects a target model and executes chasing for it by a designed chasing oracle, during which process IPOC produces accurate confidence intervals. The effectiveness of IPOCis theoretically validated through sublinear regret analysis and satisfaction of confidence interval requirements. Besides, we conduct extensive experiments on 4 real-world datasets comparing with 19 baselines. To the best of our knowledge, we are the first to apply the frontier theory of online learning to time series prediction tasks.
- Open Access
- 14 October 2022
- Published by Frontiers Media SA in Frontiers in Environmental Science
- Vol. 10
Environmental effects of global value chain embedding in manufacturing industry in countries along the Belt and Road
While embedding in the global value chain (GVC), avoiding becoming a “pollution shelter” is an urgent issue that needs to be solved for the low-carbon economic development of countries along the Belt and Road. This study empirically analyzes the impact of manufacturing GVC embedding on carbon emissions and its mechanism from the perspectives of the embedding position and degree of the GVC. It then carries out group regressions by different industries, value chain embedding modes, and so on. Finally, this study constructs static and dynamic panel models to verify the nonlinear relationship between manufacturing GVC embedding and carbon emissions. The results show that the improvement of the embedding position of GVC in the manufacturing industry promotes an increase in carbon emissions; the deeper the embedding degree of GVC, the more conducive it is to carbon emissions reduction. Compared with the service industry, the impact of manufacturing GVC embedding on carbon emissions is more significant; regardless of the value chain embedding model, the deeper the embedding degree, the more conducive it is to carbon emissions reduction. Technological progress can weaken the impact of GVC embedding on carbon emissions. There is a U-shaped relationship between the GVC embedding position and carbon emissions in the manufacturing industry and an inverted U-shaped relationship between the GVC embedding degree and carbon emissions. This study provides beneficial insights for countries along the Belt and Road to embed into the GVC to avoid falling into the dilemma of “pollution growth”.
- 14 October 2022
- Published by Frontiers Media SA in Frontiers in Environmental Science
- Vol. 10
Open AccessEnvironmental effects of global value chain embedding in manufacturing industry in countries along the Belt and Road
While embedding in the global value chain (GVC), avoiding becoming a “pollution shelter” is an urgent issue that needs to be solved for the low-carbon economic development of countries along the Belt and Road. This study empirically analyzes the impact of manufacturing GVC embedding on carbon emissions and its mechanism from the perspectives of the embedding position and degree of the GVC. It then carries out group regressions by different industries, value chain embedding modes, and so on. Finally, this study constructs static and dynamic panel models to verify the nonlinear relationship between manufacturing GVC embedding and carbon emissions. The results show that the improvement of the embedding position of GVC in the manufacturing industry promotes an increase in carbon emissions; the deeper the embedding degree of GVC, the more conducive it is to carbon emissions reduction. Compared with the service industry, the impact of manufacturing GVC embedding on carbon emissions is more significant; regardless of the value chain embedding model, the deeper the embedding degree, the more conducive it is to carbon emissions reduction. Technological progress can weaken the impact of GVC embedding on carbon emissions. There is a U-shaped relationship between the GVC embedding position and carbon emissions in the manufacturing industry and an inverted U-shaped relationship between the GVC embedding degree and carbon emissions. This study provides beneficial insights for countries along the Belt and Road to embed into the GVC to avoid falling into the dilemma of “pollution growth”.