Bowen Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bowen Hu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Yadong Zhou
Ministry of Education Key Laboratory for Intelligent Networks and Network Security, Faculty of Electronic and Information Engineering, Xian Jiaotong University, Xian, China
11 shared publications - Ting Liu
Xi’an Jiaotong University
5 shared publications - Xiaohong Guan
Xi'an Jiaotong University, Xi'an, China
5 shared publications - Yuxun Zhou
Department of Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, CA, USA
4 shared publications - Haotian Liu
Ministry of Education Key Laboratory for Intelligent Networks and Network Security, Faculty of Electronic and Information Engineering, Xian Jiaotong University, Xian, China
3 shared publications - Jiang Wu
MOE KLINNS Lab, Xian Jiaotong University, Xian, China
3 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 41 (6) , 4083-4095
A Bad Data Identification Method Based on Optimal Weight-Tuning for Power System State Estimation
The weighted least squares (WLS) method has been widely used in power systems for state estimation (SE), but in the presence of gross errors, the results of WLS SE can be significantly biased. While various bad data identification (BDI) methods exist, identifying multiple bad data for SE is still challenging, especially when bad data located at leverage points can disproportionately corrupt SE accuracy. This paper proposes an Optimal-Weighted Least Squares State Estimation (OWLS-SE) method with an optimal weight-tuning strategy to address these challenges. The impact of bad data at leverage points on estimation errors is first mathematically demonstrated through a theoretical upper bound of the SE relative error. Then, the optimal dynamic weights are developed to minimize this error bound by quantifying leverage point impacts and integrating them into a multi-objective optimization framework. The proposed OWLS-SE achieves simultaneous SE and BDI within a single optimization model, eliminating conventional two-stage processing. Numerical experiments on the 6- bus system, IEEE 30-, 118- bus systems, and the 2869- bus PEGASE system demonstrate that OWLS-SE achieves superior BDI and SE accuracy with robust performance even when multiple gross errors occur at leverage points, while maintaining computational efficiency comparable to the simplest WLS method.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 41 (6) , 4083-4095
A Bad Data Identification Method Based on Optimal Weight-Tuning for Power System State Estimation
The weighted least squares (WLS) method has been widely used in power systems for state estimation (SE), but in the presence of gross errors, the results of WLS SE can be significantly biased. While various bad data identification (BDI) methods exist, identifying multiple bad data for SE is still challenging, especially when bad data located at leverage points can disproportionately corrupt SE accuracy. This paper proposes an Optimal-Weighted Least Squares State Estimation (OWLS-SE) method with an optimal weight-tuning strategy to address these challenges. The impact of bad data at leverage points on estimation errors is first mathematically demonstrated through a theoretical upper bound of the SE relative error. Then, the optimal dynamic weights are developed to minimize this error bound by quantifying leverage point impacts and integrating them into a multi-objective optimization framework. The proposed OWLS-SE achieves simultaneous SE and BDI within a single optimization model, eliminating conventional two-stage processing. Numerical experiments on the 6- bus system, IEEE 30-, 118- bus systems, and the 2869- bus PEGASE system demonstrate that OWLS-SE achieves superior BDI and SE accuracy with robust performance even when multiple gross errors occur at leverage points, while maintaining computational efficiency comparable to the simplest WLS method.
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17 (5) , 4568-4584
IGNN: An Inference Graph Neural Network for Data Sensitivity Assessment Considering Data Inference Leakage in Cyber-Physical Power Grid
Modern Cyber-Physical Power Grids (CPPG) rely heavily on fine-grained data exchange, yet they face the concealed threat of Data Inference Leakage (DIL), where attackers infer sensitive parameters from seemingly non-sensitive data. Existing risk assessment methods typically focus on direct cyber-attacks or employ static binary classifications, failing to capture the dynamic risk propagation caused by complex physical and statistical data couplings. To address this, this paper proposes a unified data sensitivity assessment framework based on a novel Inference Graph Neural Network (IGNN). We first construct an inference relation graph that integrates both model-driven and data-driven correlations. An analytic hierarchy process (AHP) model is constructed to calibrate the intrinsic sensitivity baseline. Subsequently, a novel inference-weighted Graph Attention Network (GAT) is developed to quantify the final sensitivity by aggregating the risk propagating through the inference pathways. Experiments on IEEE 30-, 57-bus, ACTIV 200-bus, and case 1354-pegase systems demonstrate that the proposed method effectively quantifies data sensitivity and identifies high-risk data susceptible to DIL, exhibiting strong robustness across different system scales. Quantitative results indicate that the high-sensitivity data identified by our method yield a highly threatening inference accuracy of up to 0.9145, significantly outperforming GCN-based and rule-based benchmarks.
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17 (5) , 4568-4584
IGNN: An Inference Graph Neural Network for Data Sensitivity Assessment Considering Data Inference Leakage in Cyber-Physical Power Grid
Modern Cyber-Physical Power Grids (CPPG) rely heavily on fine-grained data exchange, yet they face the concealed threat of Data Inference Leakage (DIL), where attackers infer sensitive parameters from seemingly non-sensitive data. Existing risk assessment methods typically focus on direct cyber-attacks or employ static binary classifications, failing to capture the dynamic risk propagation caused by complex physical and statistical data couplings. To address this, this paper proposes a unified data sensitivity assessment framework based on a novel Inference Graph Neural Network (IGNN). We first construct an inference relation graph that integrates both model-driven and data-driven correlations. An analytic hierarchy process (AHP) model is constructed to calibrate the intrinsic sensitivity baseline. Subsequently, a novel inference-weighted Graph Attention Network (GAT) is developed to quantify the final sensitivity by aggregating the risk propagating through the inference pathways. Experiments on IEEE 30-, 57-bus, ACTIV 200-bus, and case 1354-pegase systems demonstrate that the proposed method effectively quantifies data sensitivity and identifies high-risk data susceptible to DIL, exhibiting strong robustness across different system scales. Quantitative results indicate that the high-sensitivity data identified by our method yield a highly threatening inference accuracy of up to 0.9145, significantly outperforming GCN-based and rule-based benchmarks.
- 28 June 2026
- Published by Elsevier in Information Fusion
- Vol. 136
Fusing semantic and structural representations for attributed community search
- 28 June 2026
- Published by Elsevier in Information Fusion
- Vol. 136
Fusing semantic and structural representations for attributed community search
- 28 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (2) , 722-735
A Dynamic-Causal Lens of Stock Interactions: Graph Modeling From Symbolic Movement Patterns
In modern quantitative finance and portfolio-based investment, modeling latent interactions among stocks is paramount for prediction and decision-making on profit, risk management, hedging, etc. While previous studies have constructed complex stock graphs for applying sophisticated variants of graph neural networks (GNNs), existing graph modeling approaches still face two limitations: 1) Correlation-based statistical relationships fail to unveil nuanced stock interactions effectively and determine directional influence. 2) Rigid and static graphs overlook the evolving graph structure of stocks in volatile financial systems. In this paper, we propose a dynamic-causal graph neural network (DC-GNN) to discover causal interactions from the non-stationary price time series and dynamically model graph structures for stock movement prediction. More specifically, we identify the pattern prototypes of all directed stock pairs from long-term price movement knowledge to quantify their causal interactions. These prototypes capture the pattern-to-pattern correspondence across time series based on symbolic dynamics. By inferring real-time stock networks from the prototypes, we encapsulate neighbor-induced causal impacts within heterogeneous edges to model bullish, bearish, and neutral effects among stocks. Extensive experiments conducted on real-world trading data demonstrate the superiority of the proposed framework over various state-of-the-art baselines and its effectiveness, robustness, and interpretability in Fintech.
- 28 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (2) , 722-735
A Dynamic-Causal Lens of Stock Interactions: Graph Modeling From Symbolic Movement Patterns
In modern quantitative finance and portfolio-based investment, modeling latent interactions among stocks is paramount for prediction and decision-making on profit, risk management, hedging, etc. While previous studies have constructed complex stock graphs for applying sophisticated variants of graph neural networks (GNNs), existing graph modeling approaches still face two limitations: 1) Correlation-based statistical relationships fail to unveil nuanced stock interactions effectively and determine directional influence. 2) Rigid and static graphs overlook the evolving graph structure of stocks in volatile financial systems. In this paper, we propose a dynamic-causal graph neural network (DC-GNN) to discover causal interactions from the non-stationary price time series and dynamically model graph structures for stock movement prediction. More specifically, we identify the pattern prototypes of all directed stock pairs from long-term price movement knowledge to quantify their causal interactions. These prototypes capture the pattern-to-pattern correspondence across time series based on symbolic dynamics. By inferring real-time stock networks from the prototypes, we encapsulate neighbor-induced causal impacts within heterogeneous edges to model bullish, bearish, and neutral effects among stocks. Extensive experiments conducted on real-world trading data demonstrate the superiority of the proposed framework over various state-of-the-art baselines and its effectiveness, robustness, and interpretability in Fintech.
- 3 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 73 (2) , 1460-1473
A Markov Tree Model for Cascading Failure Risk Assessment in Power Grid With Uncertain Renewable Energy Generation
The increasing penetration of renewable energy generation (REG) introduces significant uncertainty into power grids, posing heightened risks for cascading failures. In this paper, a Markov tree model is proposed to assess the risk of cascading failure in power grid with uncertain REG. The model captures the diverse failure paths caused by REG uncertainty, representing the cascading failure process as a sequence of state transitions with probabilities reflecting the likelihood of state transitions. To identify critical tripping branches during cascading failure propagation, a hybrid probability-interval method is introduced. Probabilistic power flow analysis identifies branches with overload risk, while interval positional relationships rank their severity. To improve the efficiency of risk assessment, a risk-based depth-first search (R-DFS) method is proposed. This method uses estimated risk indices to prioritize high-risk failure paths while pruning low-risk paths, significantly reducing simulation time while maintaining assessment accuracy. Compared with existing models, the proposed model balances simulation efficiency and accuracy, effectively identifying high-risk failure paths under REG uncertainty. Simulation results demonstrate the impact of threshold selection on the retention of high-risk paths and simulation performance, providing insights into managing cascading failure risks in power grid with high REG penetration.
- 3 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 73 (2) , 1460-1473
A Markov Tree Model for Cascading Failure Risk Assessment in Power Grid With Uncertain Renewable Energy Generation
The increasing penetration of renewable energy generation (REG) introduces significant uncertainty into power grids, posing heightened risks for cascading failures. In this paper, a Markov tree model is proposed to assess the risk of cascading failure in power grid with uncertain REG. The model captures the diverse failure paths caused by REG uncertainty, representing the cascading failure process as a sequence of state transitions with probabilities reflecting the likelihood of state transitions. To identify critical tripping branches during cascading failure propagation, a hybrid probability-interval method is introduced. Probabilistic power flow analysis identifies branches with overload risk, while interval positional relationships rank their severity. To improve the efficiency of risk assessment, a risk-based depth-first search (R-DFS) method is proposed. This method uses estimated risk indices to prioritize high-risk failure paths while pruning low-risk paths, significantly reducing simulation time while maintaining assessment accuracy. Compared with existing models, the proposed model balances simulation efficiency and accuracy, effectively identifying high-risk failure paths under REG uncertainty. Simulation results demonstrate the impact of threshold selection on the retention of high-risk paths and simulation performance, providing insights into managing cascading failure risks in power grid with high REG penetration.
- 28 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10099-10113
Responding to News Sensitively in Stock Attention Networks via Prompt-Adaptive Trimodal Model
Modern quantitative finance and portfolio-based investment hinge on multimedia news and historical price trends for stock movement prediction. However, prior studies overlook the long tail effect in the feature distribution of stocks, inevitably leading to biased attention and thus degrading the efficiency of utilizing news. To this end, we propose a prompt-adaptive trimodal model (PA-TMM) to overcome the biased stock attention networks and tail feature scarcity problem. In this model, sentiments automatically extracted from trimodal information serve as prompts reflecting the market’s collective mood for other entities, and the interactions among stocks are dynamically inferred for integrating both news- and price-induced movements. By leveraging the movement prompt adaptation (MPA) strategy, our model proactively adapts to the feature-imbalanced phenomenon and converges toward being responsive to the news sensitively. Extensive experiments conducted on real-world datasets consistently demonstrate not only the superiority of the proposed framework over various state-of-the-art baselines, but also its effectiveness, profitability, and robustness in Fintech. The code is accessible at https://github.com/lauht/PA-TMM.
- 28 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10099-10113
Responding to News Sensitively in Stock Attention Networks via Prompt-Adaptive Trimodal Model
Modern quantitative finance and portfolio-based investment hinge on multimedia news and historical price trends for stock movement prediction. However, prior studies overlook the long tail effect in the feature distribution of stocks, inevitably leading to biased attention and thus degrading the efficiency of utilizing news. To this end, we propose a prompt-adaptive trimodal model (PA-TMM) to overcome the biased stock attention networks and tail feature scarcity problem. In this model, sentiments automatically extracted from trimodal information serve as prompts reflecting the market’s collective mood for other entities, and the interactions among stocks are dynamically inferred for integrating both news- and price-induced movements. By leveraging the movement prompt adaptation (MPA) strategy, our model proactively adapts to the feature-imbalanced phenomenon and converges toward being responsive to the news sensitively. Extensive experiments conducted on real-world datasets consistently demonstrate not only the superiority of the proposed framework over various state-of-the-art baselines, but also its effectiveness, profitability, and robustness in Fintech. The code is accessible at https://github.com/lauht/PA-TMM.
- Open Access
- 29 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 61433-61442
Enhancing the Performance of Multi-Category Text Classification via Label Relation Mining
Multi-category text classification aims to assign labels under multiple categories to each sample in the dataset. However, most researchers overlook the relationship between labels and do not effectively incorporate text and label information. To address these problems, we propose a label embedding joint cross-attention (LEJCA) model for multi-category text classification using label relations and text information. Specifically, we first input the characters of the text into the Pre-training Language Model to obtain the representation of the text. In addition, a label embedding method based on graph representation is proposed to realize multi-dimensional mining and quantitative description of label relations. Finally, a joint cross-attention (JCA) model is proposed to integrate text and label embedding representations. Experimental results on our own constructed dataset E-government document show that LEJCA ’s micro-average F1 score is improved by $9.7~{\%}$ compared to the baseline’s best result.
- 29 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 61433-61442
Open AccessEnhancing the Performance of Multi-Category Text Classification via Label Relation Mining
Multi-category text classification aims to assign labels under multiple categories to each sample in the dataset. However, most researchers overlook the relationship between labels and do not effectively incorporate text and label information. To address these problems, we propose a label embedding joint cross-attention (LEJCA) model for multi-category text classification using label relations and text information. Specifically, we first input the characters of the text into the Pre-training Language Model to obtain the representation of the text. In addition, a label embedding method based on graph representation is proposed to realize multi-dimensional mining and quantitative description of label relations. Finally, a joint cross-attention (JCA) model is proposed to integrate text and label embedding representations. Experimental results on our own constructed dataset E-government document show that LEJCA ’s micro-average F1 score is improved by $9.7~{\%}$ compared to the baseline’s best result.
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (7) , 3595-3606
Heterogeneous Dual-Dynamic Attention Network for Modeling Mutual Interplay of Stocks
Modern quantitative finance and portfolio-based investment hinge on the dependence structure among financial instruments (like stocks) for return prediction, risk management, and hedging. Several attempts have been made to leverage recent advancements in graph neural networks (GNNs) to achieve effective modeling to capture stock interactions. However, existing work suffers from the homogeneity and stationary of the predefined graph structure, and their reliance on hard-coded correlation-based relationships neglects the mutual intervention of different instruments. In this study, we propose the heterogeneous dual-dynamic attention network (HD 2 AT) to address these challenges in modeling the mutual interplay among stocks, across four key dimensions: heterogeneity, causality, structural dynamics, and lead-lag dynamics. More specifically, our method uncovers the causal interdependencies among instruments, dynamically inferring the heterogeneous network structure from real-time trading activities. Subsequently, we identify the cross-temporal propagation of interventions by integrating interactions at the node, time, and graph levels. Extensive experiments on real-world trading data demonstrate the superiority of the proposed framework over various baselines in terms of both return prediction and back-testing profitability.
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (7) , 3595-3606
Heterogeneous Dual-Dynamic Attention Network for Modeling Mutual Interplay of Stocks
Modern quantitative finance and portfolio-based investment hinge on the dependence structure among financial instruments (like stocks) for return prediction, risk management, and hedging. Several attempts have been made to leverage recent advancements in graph neural networks (GNNs) to achieve effective modeling to capture stock interactions. However, existing work suffers from the homogeneity and stationary of the predefined graph structure, and their reliance on hard-coded correlation-based relationships neglects the mutual intervention of different instruments. In this study, we propose the heterogeneous dual-dynamic attention network (HD 2 AT) to address these challenges in modeling the mutual interplay among stocks, across four key dimensions: heterogeneity, causality, structural dynamics, and lead-lag dynamics. More specifically, our method uncovers the causal interdependencies among instruments, dynamically inferring the heterogeneous network structure from real-time trading activities. Subsequently, we identify the cross-temporal propagation of interventions by integrating interactions at the node, time, and graph levels. Extensive experiments on real-world trading data demonstrate the superiority of the proposed framework over various baselines in terms of both return prediction and back-testing profitability.
- 6 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 15 (4) , 4170-4181
Data Protection Method Against Cross-Domain Inference Threat in Cyber–Physical Power Grid
Recent advancement of data-driven methods has enabled the mining of associations among various data sets, particularly those generated from cyber-physical power grids (CPPG) where different measurements may be inherently coupled by an underlying system. As such, attackers may infer sensitive parameters jointly from several publicly shared electricity data across different security domains based on their revealed associations. Traditional data protection methods, mainly focusing on reducing the risks of direct data probing, may not be applicable to properly guard sensitive information in such scenarios. In this paper, we elaborate on such a data security issue, namely cross-domain inference (CDI), and then propose the decoder-ensemble variational autoencoder (DE-VAE) which is used for noise-adding to protect against such attack. The DE-VAE is designed with a mutual information maximization scheme to preserve the original usability of the noise-added data. Meanwhile, a multi-objective optimization is solved to achieve a trade-off between privacy protection and data usability. Our protection method is evaluated on experiments involving four real-world scenarios in the modern sensor-rich smart power grid. The experimental results show that our method can provide effective protection ability against CDI threats without sacrificing much usability, and achieves a performance gain of more than 45% compared to several non-trivial baselines.
- 6 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 15 (4) , 4170-4181
Data Protection Method Against Cross-Domain Inference Threat in Cyber–Physical Power Grid
Recent advancement of data-driven methods has enabled the mining of associations among various data sets, particularly those generated from cyber-physical power grids (CPPG) where different measurements may be inherently coupled by an underlying system. As such, attackers may infer sensitive parameters jointly from several publicly shared electricity data across different security domains based on their revealed associations. Traditional data protection methods, mainly focusing on reducing the risks of direct data probing, may not be applicable to properly guard sensitive information in such scenarios. In this paper, we elaborate on such a data security issue, namely cross-domain inference (CDI), and then propose the decoder-ensemble variational autoencoder (DE-VAE) which is used for noise-adding to protect against such attack. The DE-VAE is designed with a mutual information maximization scheme to preserve the original usability of the noise-added data. Meanwhile, a multi-objective optimization is solved to achieve a trade-off between privacy protection and data usability. Our protection method is evaluated on experiments involving four real-world scenarios in the modern sensor-rich smart power grid. The experimental results show that our method can provide effective protection ability against CDI threats without sacrificing much usability, and achieves a performance gain of more than 45% compared to several non-trivial baselines.
- 27 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (4) , 5924-5936
Estimating Nodal Admittance Matrix for Ill-Posed Inverse Power Flow Problem in Power Grid
The estimation of the nodal admittance matrix is an important problem for the power grid operation and computing tasks. Some studies have shown that the admittance matrix can be fuzzily estimated only by the injection power measurements. Nevertheless, the estimation results of most existing efforts are not ideal because of the problem's nonconvex properties, and the effects of measurement observability on the accuracy of estimation methods are not clear either. In this article, we establish an ill-posed inverse dc power flow (IDCPF) problem model and propose an admittance matrix estimation method based on multimeasurements of the power grid, including measurements of injection power and voltage phasor. Our approach converts the original problem into solvable linear subproblems and improves the estimation models by considering various physical mechanisms of the power grid. Additionally, we develop an optimization algorithm that leverages alternating least-square and alternating direction methods of multipliers for solving the IDCPF problem. We also demonstrate the detailed analysis and proof of the effects of phasor measurement observability on the accuracy of the estimation. The effectiveness and performance of our method are verified based on experiments using IEEE 30-bus and 118-bus systems.
- 27 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (4) , 5924-5936
Estimating Nodal Admittance Matrix for Ill-Posed Inverse Power Flow Problem in Power Grid
The estimation of the nodal admittance matrix is an important problem for the power grid operation and computing tasks. Some studies have shown that the admittance matrix can be fuzzily estimated only by the injection power measurements. Nevertheless, the estimation results of most existing efforts are not ideal because of the problem's nonconvex properties, and the effects of measurement observability on the accuracy of estimation methods are not clear either. In this article, we establish an ill-posed inverse dc power flow (IDCPF) problem model and propose an admittance matrix estimation method based on multimeasurements of the power grid, including measurements of injection power and voltage phasor. Our approach converts the original problem into solvable linear subproblems and improves the estimation models by considering various physical mechanisms of the power grid. Additionally, we develop an optimization algorithm that leverages alternating least-square and alternating direction methods of multipliers for solving the IDCPF problem. We also demonstrate the detailed analysis and proof of the effects of phasor measurement observability on the accuracy of the estimation. The effectiveness and performance of our method are verified based on experiments using IEEE 30-bus and 118-bus systems.