Xiaoge Zhang
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
Xiaoge Zhang has a total of 167 co-authors. Here are the top co-authors by number of shared publications:
Sankaran Mahadevan
Vanderbilt University, Department of Civil and Environmental Engineering, Vanderbilt University, 400 24th Avenue South, Nashville, 37212, TN, USA, Nashville, Tennessee, 37240-0002, UNITED STATES
22 shared publications- Yong Deng
University of Electronic Science and Technology of China
18 shared publications - Felix Tung Sun Chan
Department of Decision Sciences, Macau University of Science and Technology, Macao SAR, China
10 shared publications Andrew Adamatzky
Unconventional Computing Center, University of the West of England, Bristol, UK
9 shared publications- Jing-Xiao Liao
Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China; School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin, China; Department of Data Science, City University of Hong Kong, Hong Kong Special Administrative Region of China
9 shared publications - Shiping Zhang
School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin, China
8 shared publications
Latest Publications
- Open Access
- 23 June 2026
- Published by Springer Nature in Nature Biomedical Engineering
Implementing trust in non-small cell lung cancer diagnosis with a conformalized uncertainty-aware AI framework
Ensuring trustworthiness is fundamental in cancer diagnostics, where a misdiagnosis can have dire consequences. Current pathology AI models lack systematic solutions to address trustworthiness concerns arising from model limitations and data discrepancies between model deployment and development environments. Here we introduce TRUECAM (Trustworthiness-focused, Uncertainty-aware, End-to-end Cancer diagnosis with Model-agnostic capabilities), a framework designed to ensure both data and model trustworthiness for non-small cell lung cancer subtyping with whole-slide images. TRUECAM integrates (1) a spectral-normalized neural Gaussian process for identifying out-of-scope inputs, (2) an ambiguity-guided tile elimination to filter out highly ambiguous regions, addressing data trustworthiness, and (3) conformal prediction to ensure controlled error rates. We systematically evaluated TRUECAM across multiple cancer datasets using both task-specific and foundation models. Computational experiments suggest that models wrapped with TRUECAM consistently outperformed their unwrapped counterparts in classification accuracy, robustness, interpretability, data efficiency and fairness. These findings establish TRUECAM as a versatile framework for the responsible deployment of pathology AI in real-world settings.
- 23 June 2026
- Published by Springer Nature in Nature Biomedical Engineering
Open AccessImplementing trust in non-small cell lung cancer diagnosis with a conformalized uncertainty-aware AI framework
Ensuring trustworthiness is fundamental in cancer diagnostics, where a misdiagnosis can have dire consequences. Current pathology AI models lack systematic solutions to address trustworthiness concerns arising from model limitations and data discrepancies between model deployment and development environments. Here we introduce TRUECAM (Trustworthiness-focused, Uncertainty-aware, End-to-end Cancer diagnosis with Model-agnostic capabilities), a framework designed to ensure both data and model trustworthiness for non-small cell lung cancer subtyping with whole-slide images. TRUECAM integrates (1) a spectral-normalized neural Gaussian process for identifying out-of-scope inputs, (2) an ambiguity-guided tile elimination to filter out highly ambiguous regions, addressing data trustworthiness, and (3) conformal prediction to ensure controlled error rates. We systematically evaluated TRUECAM across multiple cancer datasets using both task-specific and foundation models. Computational experiments suggest that models wrapped with TRUECAM consistently outperformed their unwrapped counterparts in classification accuracy, robustness, interpretability, data efficiency and fairness. These findings establish TRUECAM as a versatile framework for the responsible deployment of pathology AI in real-world settings.
- 22 June 2026
- Published by Elsevier in Decision Support Systems
- Vol. 208
DISCO: Decoupling representation learning and risk control for reliable credit card fraud detection
- 22 June 2026
- Published by Elsevier in Decision Support Systems
- Vol. 208
DISCO: Decoupling representation learning and risk control for reliable credit card fraud detection
- 19 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109143
Heterogeneous neural blind deconvolution: A signal processing-empowered foundation feature extractor for bearing fault diagnosis
- 19 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109143
Heterogeneous neural blind deconvolution: A signal processing-empowered foundation feature extractor for bearing fault diagnosis
- Open Access
- 18 March 2026
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 272
A hierarchical imprecise probability approach to reliability assessment of large language models
- 18 March 2026
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 272
Open AccessA hierarchical imprecise probability approach to reliability assessment of large language models
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 1266-1280
A Class-Aware Supervised Contrastive Quadratic Neural Network for Imbalanced Bearing Fault Diagnosis
Deep learning holds significant potential for bearing fault diagnosis; however, its effectiveness is often hindered by the pervasive issue of imbalanced data in industrial settings, where fault events are inherently rare. To address this widespread challenge, we propose the Class-Aware Supervised Contrastive Quadratic Neural Network (CCQNet), a novel framework combining a class-aware supervised contrastive learning scheme with a quadratic neural network backbone. Our approach introduces two key components to tackle data imbalance: a class-weighted contrastive loss and a logit adjusted cross-entropy loss, which work in tandem to ensure the model pays equal attention to both majority and minority classes. Additionally, we enhance feature extraction through a quadratic convolutional residual network, and provide a novel theoretical analysis linking the function of the quadratic neuron to the principle of autocorrelation in signal processing. Comprehensive experiments on both public and proprietary datasets demonstrate that CCQNet substantially outperforms state-of-the-art methods, particularly in scenarios with extreme data imbalance. The source code is publicly available at https://github.com/yuweien1220/CCQNet for evaluation and validation.
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 1266-1280
A Class-Aware Supervised Contrastive Quadratic Neural Network for Imbalanced Bearing Fault Diagnosis
Deep learning holds significant potential for bearing fault diagnosis; however, its effectiveness is often hindered by the pervasive issue of imbalanced data in industrial settings, where fault events are inherently rare. To address this widespread challenge, we propose the Class-Aware Supervised Contrastive Quadratic Neural Network (CCQNet), a novel framework combining a class-aware supervised contrastive learning scheme with a quadratic neural network backbone. Our approach introduces two key components to tackle data imbalance: a class-weighted contrastive loss and a logit adjusted cross-entropy loss, which work in tandem to ensure the model pays equal attention to both majority and minority classes. Additionally, we enhance feature extraction through a quadratic convolutional residual network, and provide a novel theoretical analysis linking the function of the quadratic neuron to the principle of autocorrelation in signal processing. Comprehensive experiments on both public and proprietary datasets demonstrate that CCQNet substantially outperforms state-of-the-art methods, particularly in scenarios with extreme data imbalance. The source code is publicly available at https://github.com/yuweien1220/CCQNet for evaluation and validation.
- Top Cited Papers
- 14 February 2026
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 274
Conformal machine learning for reliable anomaly detection in industrial cyber-physical systems
- 14 February 2026
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 274
Top Cited PapersConformal machine learning for reliable anomaly detection in industrial cyber-physical systems
- Open Access
- 10 February 2026
- Published by Elsevier in SSRN Electronic Journal
Generative Digital Twin: A Sparse-xLSTM Based Self-evolving Hybrid Modeling Approach for Complex Equipment
The integration of generative artificial intelligence (GenAI) into digital twins (DTs) offers transformative potential for characterizing the non-linear dynamics of complex equipment. However, realizing high-fidelity, self-evolving generative DTs remains challenging due to the computational prohibitiveness of Transformer-based architectures and the insufficient long-term memory of traditional recurrent networks. To address these limitations, this paper proposes a novel generative digital twin (GDT) method driven by a Physics-Guided Sparse-xLSTM.First, we construct a Sparse-xLSTM architecture designed to model high-dimensional temporal dynamics efficiently. By leveraging exponential gating and matrix memory, this architecture achieves linear computational complexity while effectively capturing long-range dependencies, overcoming the quadratic bottleneck of conventional attention mechanisms. A sparse attention strategy is further incorporated to extract distinct state features from noisy sensor data for enhancing representation robustness.Second, to ensure physical consistency and generalization, a hybrid modeling mechanism is devised. Physical priors are embedded as input feature, and governing equations are integrated into the optimization objective as physical constraints, effectively confining the generative solution space to physically valid trajectories and mitigating model hallucinations.Third, addressing the imperative for continuous adaptation, a low-rank adaptation (LoRA)-based self-evolution engine is developed. This mechanism enables the GDT to perform online updates using limited streaming data by fine-tuning low-rank matrices, ensuring rapid synchronization with the time-varying states of the physical entity without catastrophic forgetting.Experimental validation on CNC machine tool wear datasets demonstrates that the proposed approach significantly outperforms state-of-the-art baselines in both prediction accuracy and adaptation efficiency, providing a robust paradigm for intelligent predictive maintenance of complex equipment.
- 10 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessGenerative Digital Twin: A Sparse-xLSTM Based Self-evolving Hybrid Modeling Approach for Complex Equipment
The integration of generative artificial intelligence (GenAI) into digital twins (DTs) offers transformative potential for characterizing the non-linear dynamics of complex equipment. However, realizing high-fidelity, self-evolving generative DTs remains challenging due to the computational prohibitiveness of Transformer-based architectures and the insufficient long-term memory of traditional recurrent networks. To address these limitations, this paper proposes a novel generative digital twin (GDT) method driven by a Physics-Guided Sparse-xLSTM.First, we construct a Sparse-xLSTM architecture designed to model high-dimensional temporal dynamics efficiently. By leveraging exponential gating and matrix memory, this architecture achieves linear computational complexity while effectively capturing long-range dependencies, overcoming the quadratic bottleneck of conventional attention mechanisms. A sparse attention strategy is further incorporated to extract distinct state features from noisy sensor data for enhancing representation robustness.Second, to ensure physical consistency and generalization, a hybrid modeling mechanism is devised. Physical priors are embedded as input feature, and governing equations are integrated into the optimization objective as physical constraints, effectively confining the generative solution space to physically valid trajectories and mitigating model hallucinations.Third, addressing the imperative for continuous adaptation, a low-rank adaptation (LoRA)-based self-evolution engine is developed. This mechanism enables the GDT to perform online updates using limited streaming data by fine-tuning low-rank matrices, ensuring rapid synchronization with the time-varying states of the physical entity without catastrophic forgetting.Experimental validation on CNC machine tool wear datasets demonstrates that the proposed approach significantly outperforms state-of-the-art baselines in both prediction accuracy and adaptation efficiency, providing a robust paradigm for intelligent predictive maintenance of complex equipment.
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 56 (3) , 1895-1910
Causality-Informed Neural Networks for Regularized Learning in Regression Problems
Neural networks that overlook the underlying causal relationships among observed variables pose significant risks in high-stakes decision-making contexts due to concerns about the robustness and stability of model performance. To tackle this issue, we present a general approach for embedding hierarchical causal structure among observed variables into a neural network to inform its learning. The proposed methodology, termed causality-informed neural network (CINN), exploits hierarchical causal structure learned from observational data as a structurally informed prior to guide the layer-to-layer architectural design of the neural network while maintaining the orientation of causal relationships in the discovered causal graph. The proposed method involves three steps. First, CINN mines causal relationships from observational data via directed acyclic graph (DAG) learning, where causal discovery is recast as a continuous optimization problem to circumvent the combinatorial nature of DAG learning. Second, we encode the discovered hierarchical causal graph among observed variables into a neural network via a dedicated architecture and loss function. By classifying observed variables in the DAG as root, intermediate, and leaf nodes, we translate the hierarchical causal DAG into CINN by creating a one-to-one correspondence between DAG nodes and certain CINN neurons. For the loss function, both intermediate and leaf nodes in the DAG are treated as target outputs during CINN training, facilitating the co-learning of causal relationships among the observed variables. Finally, as multiple loss components emerge in CINN, we leverage the projection of conflicting gradients (PCGrads) to mitigate the gradient interference among the multiple learning tasks. Computational studies indicate that CINN outperforms several state-of-the-art methods across a broad range of datasets. In addition, an ablation study that incrementally incorporates structural and quantitative causal knowledge into the neural network is conducted to highlight the pivotal role of causal knowledge in enhancing neural network’s prediction performance.
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 56 (3) , 1895-1910
Causality-Informed Neural Networks for Regularized Learning in Regression Problems
Neural networks that overlook the underlying causal relationships among observed variables pose significant risks in high-stakes decision-making contexts due to concerns about the robustness and stability of model performance. To tackle this issue, we present a general approach for embedding hierarchical causal structure among observed variables into a neural network to inform its learning. The proposed methodology, termed causality-informed neural network (CINN), exploits hierarchical causal structure learned from observational data as a structurally informed prior to guide the layer-to-layer architectural design of the neural network while maintaining the orientation of causal relationships in the discovered causal graph. The proposed method involves three steps. First, CINN mines causal relationships from observational data via directed acyclic graph (DAG) learning, where causal discovery is recast as a continuous optimization problem to circumvent the combinatorial nature of DAG learning. Second, we encode the discovered hierarchical causal graph among observed variables into a neural network via a dedicated architecture and loss function. By classifying observed variables in the DAG as root, intermediate, and leaf nodes, we translate the hierarchical causal DAG into CINN by creating a one-to-one correspondence between DAG nodes and certain CINN neurons. For the loss function, both intermediate and leaf nodes in the DAG are treated as target outputs during CINN training, facilitating the co-learning of causal relationships among the observed variables. Finally, as multiple loss components emerge in CINN, we leverage the projection of conflicting gradients (PCGrads) to mitigate the gradient interference among the multiple learning tasks. Computational studies indicate that CINN outperforms several state-of-the-art methods across a broad range of datasets. In addition, an ablation study that incrementally incorporates structural and quantitative causal knowledge into the neural network is conducted to highlight the pivotal role of causal knowledge in enhancing neural network’s prediction performance.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (2) , 2121-2135
A Unified Uncertainty-Informed Approach for Risk Management of Deep Learning Models in the Open World
Equipping deep learning models with a principled uncertainty quantification (UQ) has become essential to ensure their reliable performance in open-world environments. To address uncertainty arising from two prevalent sources - distribution shifts and out-of-distribution (OOD) inputs, this paper presents a unified, uncertainty-informed approach for quantifying and managing the risks these factors pose to deep learning models. Toward this goal, we leverage a principled UQ approach, Spectral-normalized Neural Gaussian Process (SNGP), to quantify the epistemic uncertainty associated with model predictions. Unlike other UQ methods in the literature, SNGP offers two distinctive properties: (1) spectral normalization applied to hidden layer weights to preserve relative distances among data points throughout feature transformations, and (2) replacement of the output layer with a Gaussian process to produce distance-aware uncertainty estimates. Using the uncertainty estimates from SNGP, we employ Youden's index to derive an optimal threshold that categorizes predictions into different risk levels, enabling uncertainty-informed decision making. Experiments on two datasets of varying scale demonstrate that the proposed method facilitates effective risk assessment and management in open-world settings. Computational results show that the proposed method achieves predictive performance comparable to Monte Carlo dropout and deep ensembles, while providing more computationally efficient, consistent, and principled uncertainty estimates under no shift, distribution shift, and OOD conditions.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (2) , 2121-2135
A Unified Uncertainty-Informed Approach for Risk Management of Deep Learning Models in the Open World
Equipping deep learning models with a principled uncertainty quantification (UQ) has become essential to ensure their reliable performance in open-world environments. To address uncertainty arising from two prevalent sources - distribution shifts and out-of-distribution (OOD) inputs, this paper presents a unified, uncertainty-informed approach for quantifying and managing the risks these factors pose to deep learning models. Toward this goal, we leverage a principled UQ approach, Spectral-normalized Neural Gaussian Process (SNGP), to quantify the epistemic uncertainty associated with model predictions. Unlike other UQ methods in the literature, SNGP offers two distinctive properties: (1) spectral normalization applied to hidden layer weights to preserve relative distances among data points throughout feature transformations, and (2) replacement of the output layer with a Gaussian process to produce distance-aware uncertainty estimates. Using the uncertainty estimates from SNGP, we employ Youden's index to derive an optimal threshold that categorizes predictions into different risk levels, enabling uncertainty-informed decision making. Experiments on two datasets of varying scale demonstrate that the proposed method facilitates effective risk assessment and management in open-world settings. Computational results show that the proposed method achieves predictive performance comparable to Monte Carlo dropout and deep ensembles, while providing more computationally efficient, consistent, and principled uncertainty estimates under no shift, distribution shift, and OOD conditions.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75, 3579-3589
A Unified Framework for Reliable Deep Learning: Conformal Prediction Meets Out-of-Distribution Detection
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75, 3579-3589
A Unified Framework for Reliable Deep Learning: Conformal Prediction Meets Out-of-Distribution Detection