Hong Wang

AAAI Conference 2026 Conference Paper

HGATSolver: A Heterogeneous Graph Attention Solver for Fluid–Structure Interaction

• Qin-Yi Zhang
• Hong Wang
• Siyao Liu
• Haichuan Lin
• Linying Cao
• Xiao-Hu Zhou
• Chen Chen
• Shuang-Yi Wang

Fluid–structure interaction (FSI) systems involve distinct physical domains, fluid and solid, governed by different partial differential equations and coupled at a dynamic interface. While learning-based solvers offer a promising alternative to costly numerical simulations, existing methods struggle to capture the heterogeneous dynamics of FSI within a unified framework. This challenge is further exacerbated by inconsistencies in response across domains due to interface coupling and by disparities in learning difficulty across fluid and solid regions, leading to instability during prediction. To address these challenges, we propose the Heterogeneous Graph Attention Solver (HGATSolver). HGATSolver encodes the system as a heterogeneous graph, embedding physical structure directly into the model via distinct node and edge types for fluid, solid, and interface regions. This enables specialized message-passing mechanisms tailored to each physical domain. To stabilize explicit time stepping, we introduce a novel physics-conditioned gating mechanism that serves as a learnable, adaptive relaxation factor. Furthermore, an Inter-domain Gradient-Balancing Loss dynamically balances the optimization objectives across domains based on predictive uncertainty. Extensive experiments on two constructed FSI benchmarks and a public dataset demonstrate that HGATSolver achieves state-of-the-art performance, establishing an effective framework for surrogate modeling of coupled multi-physics systems.

AAAI Conference 2026 Conference Paper

Learning Neural Operators from Partial Observations via Latent Autoregressive Modeling

• Jingren Hou
• Hong Wang
• Pengyu Xu
• Chang Gao
• Huafeng Liu
• Liping Jing

Real-world scientific applications frequently encounter incomplete observational data due to sensor limitations, geographic constraints, or measurement costs. Although neural operators significantly advanced PDE solving in terms of computational efficiency and accuracy, their underlying assumption of fully-observed spatial inputs severely restricts applicability in real-world application. We introduce the first systematic framework for learning neural operators from partial observation. We identify and formalize two fundamental obstacles: (i) the supervision gap in unobserved regions that prevents effective learning of physical correlations, and (ii) the dynamic spatial mismatch between incomplete inputs and complete solution fields. Specifically, our proposed LANO (Latent Autoregressive Neural Operator) introduces two novel components designed explicitly to address the core difficulties of partial observations: (i) a mask-to-predict training strategy that creates artificial supervision by strategically masking observed regions, and (ii) a Physics-Aware Latent Propagator that reconstructs solutions through boundary-first autoregressive generation in latent space. Additionally, we develop POBench-PDE, a dedicated and comprehensive benchmark designed specifically for evaluating neural operators under partial observation conditions across three PDE-governed tasks. LANO achieves state-of-the-art performance with relative error reductions ranging from eighteen to sixty-nine percent across all benchmarks under patch-wise missingness with missing rates below fifty percent, including real-world climate prediction. Our approach effectively addresses practical scenarios with missing rates of up to seventy-five percent, to some extent bridging the existing gap between idealized research settings and the complexities of real-world scientific computing.

EAAI Journal 2025 Journal Article

An integrated exergy efficiency and machine learning method for optimizing organic solid waste gasification process

• Wenni Chen
• Xianan Xiang
• Sha Liu
• Jun Guo
• Tao Li
• Xuehua Zhou
• Deyong Peng
• Zhiya Deng

Organic solid waste (OSW) gasification is a critical pathway toward sustainable energy utilization. This study develops an integrated prediction model by combining exergy efficiency-based analytic hierarchy process-fuzzy comprehensive evaluation (AHP-FCE) with machine learning techniques. The model aims to select the optimal gasifier type and operational parameters based on OSW characteristics and processing capacities. Exergy efficiency derived from experimental data is used to construct AHP-FCE scores, which are then predicted using eight machine learning algorithms. Gradient boosting decision tree (GBDT) achieves the best performance. The prediction model is applied to three practical cases. For a project with an annual processing capacity of 2000 tons of refuse-derived fuel (RDF), the model consistently recommends the downdraft fixed-bed gasifier (DBG). In a corn straw gasification project processing 11, 000 tons per year, the bubbling fluidized-bed gasifier (BBG) is identified as the optimal choice. For a bamboo chip gasification project with an annual capacity of 150, 000 tons, the model suggests using the circulating fluidized-bed gasifier (CFBG) for reduction objectives and the dual fluidized-bed gasifier (DFBG) for hydrogen production goals. Additionally, the model shows significant potential. It can also be applied to optimize other complex systems that require balancing multiple influencing factors.

AIIM Journal 2025 Journal Article

EDDINet: Enhancing drug–drug interaction prediction via information flow and consensus constrained multi-graph contrastive learning

• Hong Wang
• Luhe Zhuang
• Yijie Ding
• Prayag Tiwari
• Cheng Liang

Predicting drug–drug interactions (DDIs) is crucial for understanding and preventing adverse drug reactions (ADRs). However, most existing methods inadequately explore the interactive information between drugs in a self-supervised manner, limiting our comprehension of drug–drug associations. This paper introduces EDDINet: Enhancing Drug-Drug Interaction Prediction via Information Flow and Consensus-Constrained Multi-Graph Contrastive Learning for precise DDI prediction. We first present a cross-modal information-flow mechanism to integrate diverse drug features, enriching the structural insights conveyed by the drug feature vector. Next, we employ contrastive learning to filter various biological networks, enhancing the model’s robustness. Additionally, we propose a consensus regularization framework that collaboratively trains multi-view models, producing high-quality drug representations. To unify drug representations derived from different biological information, we utilize an attention mechanism for DDI prediction. Extensive experiments demonstrate that EDDINet surpasses state-of-the-art unsupervised models and outperforms some supervised baseline models in DDI prediction tasks. Our approach shows significant advantages and holds promising potential for advancing DDI research and improving drug safety assessments. Our codes are available at: https: //github. com/95LY/EDDINet_code.

EAAI Journal 2025 Journal Article

Gait pattern recognition based on electroencephalogram signals with common spatial pattern and graph attention networks

• Yanzheng Lu
• Hong Wang
• Zhiguo Lu
• Jianye Niu
• Chong Liu

Assisting human locomotion in various gait patterns is one of the challenges in the interaction between human and lower limb exoskeleton. In this paper, we propose the graph attention network with electroencephalogram (EEG) signal graph structure data constructed by common spatial pattern (CSP) model to extract the spatial–temporal information from multi-channel EEG signals to recognize gait patterns including walk, run, stair descent, stair ascent, stand-to-sit, sit-to-stand, and jump. The CSP spatial filters are analyzed for EEG signals with multiple gait patterns. The EEG signal graph structure data is constructed based on the spatial–temporal features and spatial domain features of the CSP filtered data. The graph structure based on the correlation between channels and the graph structure based on the spatial relative position of EEG electrodes are constructed for comparison. The gait pattern recognition performance of the proposed model is significantly higher than that of comparison models, and the average recognition accuracy is 86. 747%. The accuracy of gait pattern recognition along gait cycle is analyzed. Based on the analysis of the EEG signal graph structure reconstructed by multi-head attention coefficients of the proposed model, the learning characteristics of the model can be obtained. The relationship between EEG channels is analyzed based on the graph structures the models focusing on. Finally, the proposed method is validated on the open access brain-computer interface (BCI) competition IV Datasets 2a of EEG signals.

NeurIPS Conference 2025 Conference Paper

Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training

• Hong Wang
• Haiyang Xin
• Jie Wang
• Xuanze Yang
• Fei Zha
• huanshuo dong
• Yan Jiang

Pre-training has proven effective in addressing data scarcity and performance limitations in solving PDE problems with neural operators. However, challenges remain due to the heterogeneity of PDE datasets in equation types, which leads to high errors in mixed training. Additionally, dense pre-training models that scale parameters by increasing network width or depth incur significant inference costs. To tackle these challenges, we propose a novel M ixture- o f- E xperts P re-training O perator T ransformer ( MoE-POT ), a sparse-activated architecture that scales parameters efficiently while controlling inference costs. Specifically, our model adopts a layer-wise router-gating network to dynamically select 4 routed experts from 16 expert networks during inference, enabling the model to focus on equation-specific features. Meanwhile, we also integrate 2 shared experts, aiming to capture common properties of PDE and reduce redundancy among routed experts. The final output is computed as the weighted average of the results from all activated experts. We pre-train models with parameters from 30M to 0. 5B on 6 public PDE datasets. Our model with 90M activated parameters achieves up to a 40\% reduction in zero-shot error compared with existing models with 120M activated parameters. Additionally, we conduct interpretability analysis, showing that dataset types can be inferred from router-gating network decisions, which validates the rationality and effectiveness of the MoE architecture.

JBHI Journal 2025 Journal Article

Step Width Estimation in Individuals With and Without Neurodegenerative Disease via a Novel Data-Augmentation Deep Learning Model and Minimal Wearable Inertial Sensors

• Hong Wang
• Zakir Ullah
• Eran Gazit
• Marina Brozgol
• Tian Tan
• Jeffrey M. Hausdorff
• Peter B. Shull
• Penina Ponger

Step width is vital for gait stability, postural balance control, and fall risk reduction. However, estimating step width typically requires either fixed cameras or a full kinematic body suit of wearable inertial measurement units (IMUs), both of which are often too expensive and time-consuming for clinical application. We thus propose a novel data-augmented deep learning model for estimating step width in individuals with and without neurodegenerative disease using a minimal set of wearable IMUs. Twelve patients with neurodegenerative, clinically diagnosed Spinocerebellar ataxia type 3 (SCA3) performed over ground walking trials, and seventeen healthy individuals performed treadmill walking trials at various speeds and gait modifications while wearing IMUs on each shank and the pelvis. Results demonstrated step width mean absolute errors of 3. 3 $\pm$ 0. 7 cm and 2. 9 $\pm$ 0. 5 cm for the neurodegenerative and healthy groups, respectively, which were below the minimal clinically important difference of 6. 0 cm. Step width variability mean absolute errors were 1. 5 cm and 0. 8 cm for neurodegenerative and healthy groups, respectively. Data augmentation significantly improved accuracy performance in the neurodegenerative group, likely because they exhibited larger variations in walking kinematics as compared with healthy subjects. These results could enable clinically meaningful and accurate portable step width monitoring for individuals with and without neurodegenerative disease, potentially enhancing rehabilitative training, assessment, and dynamic balance control in clinical and real-life settings.

NeurIPS Conference 2025 Conference Paper

STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem

• Hong Wang
• Yixuan Jiang
• Jie Wang
• Xinyi Li
• Jian Luo
• huanshuo dong

Operator eigenvalue problems play a critical role in various scientific fields and engineering applications, yet numerical methods are hindered by the curse of dimensionality. Recent deep learning methods provide an efficient approach to address this challenge by iteratively updating neural networks. These methods' performance relies heavily on the spectral distribution of the given operator: larger gaps between the operator's eigenvalues will improve precision, thus tailored spectral transformations that leverage the spectral distribution can enhance their performance. Based on this observation, we propose the S pectral T ransformation Net work ( STNet ). During each iteration, STNet uses approximate eigenvalues and eigenfunctions to perform spectral transformations on the original operator, turning it into an equivalent but easier problem. Specifically, we employ deflation projection to exclude the subspace corresponding to already solved eigenfunctions, thereby reducing the search space and avoiding converging to existing eigenfunctions. Additionally, our filter transform magnifies eigenvalues in the desired region and suppresses those outside, further improving performance. Extensive experiments demonstrate that STNet consistently outperforms existing learning-based methods, achieving state-of-the-art performance in accuracy.

NeurIPS Conference 2025 Conference Paper

SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning

• Hong Wang
• Jie Wang
• Minghao Ma
• Haoran Shao
• Haoyang Liu

Matrix preconditioning is a critical technique to accelerate the solution of linear systems, where performance heavily depends on the selection of preconditioning parameters. Traditional parameter selection approaches often define fixed constants for specific scenarios. However, they rely on domain expertise and fail to consider the instance-wise features for individual problems, limiting their performance. In contrast, machine learning (ML) approaches, though promising, are hindered by high inference costs and limited interpretability. To combine the strengths of both approaches, we propose a symbolic discovery framework—namely, Sym bolic Ma trix P reconditioning ( SymMaP )—to learn efficient symbolic expressions for preconditioning parameters. Specifically, we employ a neural network to search the high-dimensional discrete space for expressions that can accurately predict the optimal parameters. The learned expression allows for high inference efficiency and excellent interpretability (expressed in concise symbolic formulas), making it simple and reliable for deployment. Experimental results show that SymMaP consistently outperforms traditional strategies across various benchmarks.

EAAI Journal 2025 Journal Article

Unsupervised multi-view feature selection based on weighted low-rank tensor learning and its application in multi-omics datasets

• Daoyuan Wang
• Lianzhi Wang
• Wenlan Chen
• Hong Wang
• Cheng Liang

With the explosive growth of unlabeled multi-view data with high dimensionality in various fields such as bioinformatics, unsupervised multi-view feature selection has become a key technique to simultaneously handle the curse of dimensionality in multiple datasets. Most existing methods heavily rely on the pseudo labels obtained from respective views, where they perform feature selections without comprehensively exploiting the high-order connections among views. In this paper, we propose a weighted low-rank tensor-based unsupervised multi-view feature selection framework (WLTL), which integrates multi-view spectral clustering and weighted low-rank tensor to generate high-quality pseudo labels for feature selection. Specifically, we stack the clustering indicator matrices into a three-dimensional tensor and impose the weighted tensor nuclear norm constraint, which captures high-order correlations and consistent pseudo label information while allowing for more refined consideration of the importance of each view. Our method also features an adaptive strategy to automatically assign view weights, optimizing the feature selection process by considering both individual view characteristics and inter-view relationships. We present an efficient optimization algorithm for iteratively refining the proposed framework. Extensive experiments implemented on six machine learning and three multi-omics datasets confirm the superiority of WLTL. Additionally, the case study performed on the cancer dataset serves to affirm the practicality of our model.

EAAI Journal 2024 Journal Article

A novel multi-step ahead prediction method for landslide displacement based on autoregressive integrated moving average and intelligent algorithm

• Peng Shao
• Hong Wang
• Guangyu Long
• Jianxing Liao
• Fei Gan
• Bin Xu
• Ke Hu
• Yuhang Teng

Accurate landslide displacement prediction is crucial for prevention and early warning. In this paper, we proposed a novel hybrid multi-step-ahead prediction model (ARIMA-IM) that combines autoregressive integrated moving average (ARIMA) and intelligent models (IMs) for landslide displacement prediction. This model integrates the linear prediction strengths of ARIMA, the signal decomposition capabilities of variational mode decomposition (VMD) and empirical wavelet transform (EWT), and the nonlinear change-capturing ability of IMs. The proposed model cannot only effectively capture abrupt and long-term trends in landslide displacement but also enable high-precision multi-step-ahead prediction. To validate the effectiveness of the proposed model, we predicted the displacement of the Bazimen landslide in the Three Gorges Reservoir by using four IMs, namely long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gate recurrent unit (GRU), and artificial neural network (ANN), in both continuous and jump strategies for multi-step-ahead prediction. Results showed that ARIMA-IM, especially the hybrid model combining ARIMA and deep learning, achieved high accuracy in 1–5-step-ahead prediction. Continuous multi-step-ahead prediction exhibited higher accuracy and provided more prediction information for decision-making. Compared to other models, ARIMA-IM not only achieved multi-step-ahead prediction but also exhibited comparable or better prediction accuracy, which is of high practical significance for landslide disaster early warning.

ICML Conference 2024 Conference Paper

Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment

• Chen Zhang
• Qiang He
• Yuan Zhou
• Elvis S. Liu
• Hong Wang
• Jian Zhao 0010
• Yang Wang

Deep Reinforcement Learning (DRL) agents have demonstrated impressive success in a wide range of game genres. However, existing research primarily focuses on optimizing DRL competence rather than addressing the challenge of prolonged player interaction. In this paper, we propose a practical DRL agent system for fighting games named Shūkai, which has been successfully deployed to Naruto Mobile, a popular fighting game with over 100 million registered users. Shūkai quantifies the state to enhance generalizability, introducing Heterogeneous League Training (HELT) to achieve balanced competence, generalizability, and training efficiency. Furthermore, Shūkai implements specific rewards to align the agent’s behavior with human expectations. Shūkai ’s ability to generalize is demonstrated by its consistent competence across all characters, even though it was trained on only 13% of them. Additionally, HELT exhibits a remarkable 22% improvement in sample efficiency. Shūkai serves as a valuable training partner for players in Naruto Mobile, enabling them to enhance their abilities and skills.

JBHI Journal 2024 Journal Article

BTSSPro: Prompt-Guided Multimodal Co-Learning for Breast Cancer Tumor Segmentation and Survival Prediction

• Wei Li
• Tianyu Liu
• Feiyan Feng
• Shengpeng Yu
• Hong Wang
• Yanshen Sun

Early detection significantly enhances patients' survival rates by identifying tumors in their initial stages through medical imaging. However, prevailing methodologies encounter challenges in extracting comprehensive information from diverse modalities, thereby exacerbating semantic disparities and overlooking critical task correlations, consequently compromising the accuracy of prognosis predictions. Moreover, clinical insights emphasize the advantageous sharing of parameters between tumor segmentation and survival prediction for enhanced prognostic accuracy. This paper proposes a novel model, BTSSPro, designed to concurrently address B reast cancer T umor S egmentation and S urvival prediction through a Pro mpt-guided multi-modal co-learning framework. Technologically, our approach involves the extraction of tumor-specific discriminative features utilizing shared dual attention (SDA) blocks, which amalgamate spatial and channel information from breast MR images. Subsequently, we employ a guided fusion module (GFM) to seamlessly integrate the Electronic Health Record (EHR) vector into the extracted tumor-related discriminative feature representations. This integration prompts the model's feature selection to align more closely with real-world scenarios. Finally, a feature harmonic unit (FHU) is introduced to coordinate the transformer encoder and CNN decoder, thus reducing semantic differences. Remarkably, BTSSPro achieved a C-index of 0. 968 and Dice score of 0. 715 on the Breast MRI-NACT-Pilot dataset and a C-index of 0. 807 and Dice score of 0. 791 on the ISPY1 dataset, surpassing the previous state-of-the-art methods.

TMLR Journal 2024 Journal Article

Coordinate Transform Fourier Neural Operators for Symmetries in Physical Modelings

• Wenhan Gao
• Ruichen Xu
• Hong Wang
• Yi Liu

Symmetries often arise in many natural sciences; rather than relying on data augmentation or regularization for learning these symmetries, incorporating these inherent symmetries directly into the neural network architecture simplifies the learning process and enhances model performance. The laws of physics, including partial differential equations (PDEs), remain unchanged regardless of the coordinate system employed to depict them, and symmetries sometimes can be natural to illuminate in other coordinate systems. Moreover, symmetries often are associated with the underlying domain shapes. In this work, we consider physical modelings with neural operators (NOs), and we propose an approach based on coordinate transforms (CT) to work on different domain shapes and symmetries. Canonical coordinate transforms are applied to convert both the domain shape and symmetries. For example, a sphere can be naturally converted to a square with periodicities across its edges. The resulting CT-FNO scheme barely increases computational complexity and can be applied to different domain shapes while respecting the symmetries.

JBHI Journal 2024 Journal Article

Cross-Modal Vertical Federated Learning for MRI Reconstruction

• Yunlu Yan
• Hong Wang
• Yawen Huang
• Nanjun He
• Lei Zhu
• Yong Xu
• Yuexiang Li
• Yefeng Zheng

Federated learning enables multiple hospitals to cooperatively learn a shared model without privacy disclosure. Existing methods often take a common assumption that the data from different hospitals have the same modalities. However, such a setting is difficult to fully satisfy in practical applications, since the imaging guidelines may be different between hospitals, which makes the number of individuals with the same set of modalities limited. To this end, we formulate this practical-yet-challenging cross-modal vertical federated learning task, in which data from multiple hospitals have different modalities with a small amount of multi-modality data collected from the same individuals. To tackle such a situation, we develop a novel framework, namely Federated Consistent Regularization constrained Feature Disentanglement (Fed-CRFD), for boosting MRI reconstruction by effectively exploring the overlapping samples (i. e. , same patients with different modalities at different hospitals) and solving the domain shift problem caused by different modalities. Particularly, our Fed-CRFD involves an intra-client feature disentangle scheme to decouple data into modality-invariant and modality-specific features, where the modality-invariant features are leveraged to mitigate the domain shift problem. In addition, a cross-client latent representation consistency constraint is proposed specifically for the overlapping samples to further align the modality-invariant features extracted from different modalities. Hence, our method can fully exploit the multi-source data from hospitals while alleviating the domain shift problem. Extensive experiments on two typical MRI datasets demonstrate that our network clearly outperforms state-of-the-art MRI reconstruction methods.

NeurIPS Conference 2024 Conference Paper

Neural Krylov Iteration for Accelerating Linear System Solving

• Jian Luo
• Jie Wang
• Hong Wang
• huanshuo dong
• Zijie Geng
• Hanzhu Chen
• Yufei Kuang

Solving large-scale sparse linear systems is essential in fields like mathematics, science, and engineering. Traditional numerical solvers, mainly based on the Krylov subspace iteration algorithm, suffer from the low-efficiency problem, which primarily arises from the less-than-ideal iteration. To tackle this problem, we propose a novel method, namely Neur al K rylov It era t ion ( NeurKItt ), for accelerating linear system solving. Specifically, NeurKItt employs a neural operator to predict the invariant subspace of the linear system and then leverages the predicted subspace to accelerate linear system solving. To enhance the subspace prediction accuracy, we utilize QR decomposition for the neural operator outputs and introduce a novel projection loss function for training. NeurKItt benefits the solving by using the predicted subspace to guide the iteration process, significantly reducing the number of iterations. We provide extensive experiments and comprehensive theoretical analyses to demonstrate the feasibility and efficiency of NeurKItt. In our main experiments, NeurKItt accelerates the solving of linear systems across various settings and datasets, achieving up to a 5. 5× speedup in computation time and a 16. 1× speedup in the number of iterations.

AAAI Conference 2023 Conference Paper

ClassFormer: Exploring Class-Aware Dependency with Transformer for Medical Image Segmentation

• Huimin Huang
• Shiao Xie
• Lanfen Lin
• Ruofeng Tong
• Yen-Wei Chen
• Hong Wang
• Yuexiang Li
• Yawen Huang

Vision Transformers have recently shown impressive performances on medical image segmentation. Despite their strong capability of modeling long-range dependencies, the current methods still give rise to two main concerns in a class-level perspective: (1) intra-class problem: the existing methods lacked in extracting class-specific correspondences of different pixels, which may lead to poor object coverage and/or boundary prediction; (2) inter-class problem: the existing methods failed to model explicit category-dependencies among various objects, which may result in inaccurate localization. In light of these two issues, we propose a novel transformer, called ClassFormer, powered by two appealing transformers, i.e., intra-class dynamic transformer and inter-class interactive transformer, to address the challenge of fully exploration on compactness and discrepancy. Technically, the intra-class dynamic transformer is first designed to decouple representations of different categories with an adaptive selection mechanism for compact learning, which optimally highlights the informative features to reflect the salient keys/values from multiple scales. We further introduce the inter-class interactive transformer to capture the category dependency among different objects, and model class tokens as the representative class centers to guide a global semantic reasoning. As a consequence, the feature consistency is ensured with the expense of intra-class penalization, while inter-class constraint strengthens the feature discriminability between different categories. Extensive empirical evidence shows that ClassFormer can be easily plugged into any architecture, and yields improvements over the state-of-the-art methods in three public benchmarks.

ICRA Conference 2023 Conference Paper

Failure Detection for Motion Prediction of Autonomous Driving: An Uncertainty Perspective

• Wenbo Shao
• Yanchao Xu
• Liang Peng
• Jun Li 0082
• Hong Wang

Motion prediction is essential for safe and efficient autonomous driving. However, the inexplicability and uncertainty of complex artificial intelligence models may lead to unpredictable failures of the motion prediction module, which may mislead the system to make unsafe decisions. Therefore, it is necessary to develop methods to guarantee reliable autonomous driving, where failure detection is a potential direction. Uncertainty estimates can be used to quantify the degree of confidence a model has in its predictions and may be valuable for failure detection. We propose a framework of failure detection for motion prediction from the uncertainty perspective, considering both motion uncertainty and model uncertainty, and formulate various uncertainty scores according to different prediction stages. The proposed approach is evaluated based on different motion prediction algorithms, uncertainty estimation methods, uncertainty scores, etc. , and the results show that uncertainty is promising for failure detection for motion prediction but should be used with caution.

AIIM Journal 2023 Journal Article

Predicting kidney transplant survival using multiple feature representations for HLAs

• Mohammadreza Nemati
• Haonan Zhang
• Michael Sloma
• Dulat Bekbolsynov
• Hong Wang
• Stanislaw Stepkowski
• Kevin S. Xu

Kidney transplantation can significantly enhance living standards for people suffering from end-stage renal disease. A significant factor that affects graft survival time (the time until the transplant fails and the patient requires another transplant) for kidney transplantation is the compatibility of the Human Leukocyte Antigens (HLAs) between the donor and recipient. In this paper, we propose 4 new biologically-relevant feature representations for incorporating HLA information into machine learning-based survival analysis algorithms. We evaluate our proposed HLA feature representations on a database of over 100, 000 transplants and find that they improve prediction accuracy by about 1%, modest at the patient level but potentially significant at a societal level. Accurate prediction of survival times can improve transplant survival outcomes, enabling better allocation of donors to recipients and reducing the number of re-transplants due to graft failure with poorly matched donors.

JBHI Journal 2022 Journal Article

A Novel PPG-FMG-ACC Wristband for Hand Gesture Recognition

• Hong Wang
• Peiqi Kang
• Qinghua Gao
• Shuo Jiang
• Peter B. Shull

Wrist-based hand gesture recognition has the potential to unlock naturalistic human-computer interaction for a vast array of virtual and augmented reality applications. Photoplethysmography (PPG), force myography (FMG), and accelerometry (ACC) have generally been proposed as isolated single sensing modalities for gesture recognition, but any of these alone is inherently limited in the amount of biological information it can collect during finger and hand movements. We thus propose a novel, wrist-based, PPG-FMG-ACC combined sensing approach based on a multi-head attention mechanism fusion convolutional neural network (CNN-AF) for gesture recognition. Nine subjects performed twelve hand gestures involving various wrist and finger postures. Experimental results showed that multi-modal fusion improved classification performance significantly ( $p$ $< $ 0. 01) compared to any single sensing modality, and the F1-score of the combined PPG-FMG-ACC approach was 40. 1% higher than PPG alone, 27. 4% higher than ACC alone, and 11. 9% higher than FMG alone. To the best of our knowledge, this paper is the first to combine wrist-based PPG, FMG, and ACC signals for hand gesture recognition. These results could serve to inform wrist-based gesture recognition design (e. g. , via a smartwatch) and thus expand the capabilities of intuitive and ubiquitous human-machine interaction.

IJCAI Conference 2022 Conference Paper

Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction

• Hong Wang
• Yuexiang Li
• Deyu Meng
• Yefeng Zheng

Inspired by the great success of deep neural networks, learning-based methods have gained promising performances for metal artifact reduction (MAR) in computed tomography (CT) images. However, most of the existing approaches put less emphasis on modelling and embedding the intrinsic prior knowledge underlying this specific MAR task into their network designs. Against this issue, we propose an adaptive convolutional dictionary network (ACDNet), which leverages both model-based and learning-based methods. Specifically, we explore the prior structures of metal artifacts, e. g. , non-local repetitive streaking patterns, and encode them as an explicit weighted convolutional dictionary model. Then, a simple-yet-effective algorithm is carefully designed to solve the model. By unfolding every iterative substep of the proposed algorithm into a network module, we explicitly embed the prior structure into a deep network, i. e. , a clear interpretability for the MAR task. Furthermore, our ACDNet can automatically learn the prior for artifact-free CT images via training data and adaptively adjust the representation kernels for each input CT image based on its content. Hence, our method inherits the clear interpretability of model-based methods and maintains the powerful representation ability of learning-based methods. Comprehensive experiments executed on synthetic and clinical datasets show the superiority of our ACDNet in terms of effectiveness and model generalization. Code and supplementary material are available at https: //github. com/hongwang01/ACDNet.

AAAI Conference 2022 Conference Paper

Noninvasive Lung Cancer Early Detection via Deep Methylation Representation Learning

• Xiangrui Cai
• Jinsheng Tao
• Shichao Wang
• Zhiyu Wang
• Jiaxian Wang
• Mei Li
• Hong Wang
• Xixiang Tu

Early detection of lung cancer is crucial for five-year survival of patients. Compared with the pathological analysis and CT scans, the circulating tumor DNA (ctDNA) methylation based approach is noninvasive and cost-effective, and thus is one of the most promising methods for early detection of lung cancer. Existing studies on ctDNA methylation data measure the methylation level of each region with a predefined metric, ignoring the positions of methylated CpG sites and methylation patterns, thus are not able to capture the early cancer signals. In this paper, we propose a blood-based lung cancer detection method, and present the first ever study to represent methylation regions by continuous vectors. Specifically, we propose DeepMeth to regard each region as a one-channel image and develop an auto-encoder model to learn its representation. For each ctDNA methylation sample, DeepMeth achieves its representation via concatenating the region vectors. We evaluate DeepMeth on a multicenter clinical dataset collected from 14 hospitals. The experiments show that DeepMeth achieves about 5%-8% improvements compared with the baselines in terms of Area Under the Curve (AUC). Moreover, the experiments also demonstrate that DeepMeth can be combined with traditional scalar metrics to enhance the diagnostic power of ctDNA methylation classifiers. DeepMeth has been clinically deployed and applied to 450 patients from 94 hospitals nationally since April 2020.

NeurIPS Conference 2022 Conference Paper

Towards Theoretically Inspired Neural Initialization Optimization

• Yibo Yang
• Hong Wang
• Haobo Yuan
• Zhouchen Lin

Automated machine learning has been widely explored to reduce human efforts in designing neural architectures and looking for proper hyperparameters. In the domain of neural initialization, however, similar automated techniques have rarely been studied. Most existing initialization methods are handcrafted and highly dependent on specific architectures. In this paper, we propose a differentiable quantity, named GradCoisne, with theoretical insights to evaluate the initial state of a neural network. Specifically, GradCosine is the cosine similarity of sample-wise gradients with respect to the initialized parameters. By analyzing the sample-wise optimization landscape, we show that both the training and test performance of a network can be improved by maximizing GradCosine under gradient norm constraint. Based on this observation, we further propose the neural initialization optimization (NIO) algorithm. Generalized from the sample-wise analysis into the real batch setting, NIO is able to automatically look for a better initialization with negligible cost compared with the training time. With NIO, we improve the classification performance of a variety of neural architectures on CIFAR10, CIFAR-100, and ImageNet. Moreover, we find that our method can even help to train large vision Transformer architecture without warmup.

EAAI Journal 2019 Journal Article

A fiber-reinforced human-like soft robotic manipulator based on sEMG force estimation

• Naishi Feng
• Hong Wang
• Fo Hu
• Mohamed Amin Gouda
• Jiale Gong
• Feng Wang

Before the myoelectric prosthesis become a good substitute of a natural arm, there still exist several big challenges in terms of hand structural design and control algorithms. The overall objective of this paper is to propose a new humanoid hand with specify force output under sEMG control. A fiber reinforced three-cavity structure is proposed with thumb and middle finger bendable and the rest of the fingers bendable and twistable simultaneously to imitate the finger-to-finger function. The relation between the input pressure and twist angle is derived based on the material mechanics formula and the neo-Hookean model. The force module of the soft hand and sEMG are built achieving the accuracy of 94. 2%. The experimental result has supported that the developed soft hand can be applied to artificial limb improving the quality of amputee’s life.

NeurIPS Conference 2019 Conference Paper

Optimal Analysis of Subset-Selection Based L_p Low-Rank Approximation

• Chen Dan
• Hong Wang
• Hongyang Zhang
• Yuchen Zhou
• Pradeep Ravikumar

We show that for the problem of $\ell_p$ rank-$k$ approximation of any given matrix over $R^{n\times m}$ and $C^{n\times m}$, the algorithm of column subset selection enjoys approximation ratio $(k+1)^{1/p}$ for $1\le p\le 2$ and $(k+1)^{1-1/p}$ for $p\ge 2$. This improves upon the previous $O(k+1)$ bound (Chierichetti et al. ,2017) for $p\ge 1$. We complement our analysis with lower bounds; these bounds match our upper bounds up to constant 1 when $p\geq 2$. At the core of our techniques is an application of Riesz-Thorin interpolation theorem from harmonic analysis, which might be of independent interest to other algorithmic designs and analysis more broadly. Our analysis results in improvements on approximation guarantees of several other algorithms with various time complexity. For example, to make the algorithm of column subset selection computationally efficient, we analyze a polynomial time bi-criteria algorithm which selects $O(k\log m)$ number of columns. We show that this algorithm has an approximation ratio of $O((k+1)^{1/p})$ for $1\le p\le 2$ and $O((k+1)^{1-1/p})$ for $p\ge 2$. This improves over the bound in (Chierichetti et al. ,2017) with an $O(k+1)$ approximation ratio. Our bi-criteria algorithm also implies an exact-rank method in polynomial time with a slightly larger approximation ratio.

AAAI Conference 2018 Conference Paper

Noisy Derivative-Free Optimization With Value Suppression

• Hong Wang
• Hong Qian
• Yang Yu

Derivative-free optimization has shown advantage in solving sophisticated problems such as policy search, when the environment is noise-free. Many real-world environments are noisy, where solution evaluations are inaccurate due to the noise. Noisy evaluation can badly injure derivative-free optimization, as it may make a worse solution looks better. Sampling is a straightforward way to reduce noise, while previous studies have shown that delay the noise handling to the comparison time point (i. e. , threshold selection) can be helpful for derivative-free optimization. This work further delays the noise handling, and proposes a simple noise handling mechanism, i. e. , value suppression. By value suppression, we do nothing about noise until the best-so-far solution has not been improved for a period, and then suppress the value of the best-so-far solution and continue the optimization. On synthetic problems as well as reinforcement learning tasks, experiments verify that value suppression can be significantly more effective than the previous methods.

AIIM Journal 2017 Journal Article

Random survival forest with space extensions for censored data

• Hong Wang
• Lifeng Zhou

Prediction capability of a classifier usually improves when it is built from an extended variable space by adding new variables from randomly combination of two or more original variables. However, its usefulness in survival analysis of censored time-to-event data is yet to be verified. In this research, we investigate the plausibility of space extension technique, originally proposed for classification purpose, to survival analysis. By combing random subspace, bagging and extended space techniques, we develop a random survival forest with space extensions algorithm. According to statistical analysis results, we show that the proposed model outperforms or at least comparable to popular survival models such as random survival forest, rotation survival forest, Cox proportional hazard and boosting survival models on well-known benchmark datasets.

IJCAI Conference 2016 Conference Paper

Adversarial Sequence Tagging

• Jia Li
• Kaiser Asif
• Hong Wang
• Brian D. Ziebart
• Tanya Berger-Wolf

Providing sequence tagging that minimize Hamming loss is a challenging, but important, task. Directly minimizing this loss over a training sample is generally an NP-hard problem. Instead, existing sequence tagging methods minimize a convex upper bound that upper bounds the Hamming loss. Unfortunately, this often either leads to inconsistent predictors (e. g. , max-margin methods) or predictions that are mismatched on the Hamming loss (e. g. , conditional random fields). We present adversarial sequence tagging, a consistent structured prediction framework for minimizing Hamming loss by pessimistically viewing uncertainty. Our approach pessimistically approximates the training data, yielding an adversarial game between the sequence tag predictor and the sequence labeler. We demonstrate the benefits of the approach on activity recognition and information extraction/segmentation tasks.

NeurIPS Conference 2015 Conference Paper

Adversarial Prediction Games for Multivariate Losses

• Hong Wang
• Wei Xing
• Kaiser Asif
• Brian Ziebart

Multivariate loss functions are used to assess performance in many modern prediction tasks, including information retrieval and ranking applications. Convex approximations are typically optimized in their place to avoid NP-hard empirical risk minimization problems. We propose to approximate the training data instead of the loss function by posing multivariate prediction as an adversarial game between a loss-minimizing prediction player and a loss-maximizing evaluation player constrained to match specified properties of training data. This avoids the non-convexity of empirical risk minimization, but game sizes are exponential in the number of predicted variables. We overcome this intractability using the double oracle constraint generation method. We demonstrate the efficiency and predictive performance of our approach on tasks evaluated using the precision at k, the F-score and the discounted cumulative gain.

EAAI Journal 2012 Journal Article

Hybrid intelligent parameter estimation based on grey case-based reasoning for laminar cooling process

• Guishan Xing
• Jinliang Ding
• Tianyou Chai
• Puya Afshar
• Hong Wang

In this paper, a hybrid intelligent parameter estimation algorithm is proposed for predicting the strip temperature during laminar cooling process. The algorithm combines a hybrid genetic algorithm (HGA) with grey case-based reasoning (GCBR) in order to improve the precision of the strip temperature prediction. In this context, the hybrid genetic algorithm is formed by combining the genetic algorithm with an annealing and a local multidimensional search algorithm based on deterministic inverse parabolic interpolation. Firstly, the weight vectors of retrieval features in case-based reasoning are optimised using hybrid genetic algorithm in offline mode, and then they are used in grey case-based reasoning to accurately estimate the model parameters online. The hybrid intelligent parameter estimation algorithm is validated using a set of operational data gathered from a hot-rolled strip laminar cooling process in a steel plant. Experiment results show the effectiveness of the proposed method in improving the precision of the strip temperature prediction. The proposed method can be used in real-time temperature control of hot-rolled strip and has potential for parameter estimation of different types of cooling process.

ICRA Conference 2010 Conference Paper

Quotient kinematics machines: Concept, analysis and synthesis

• Yuanqing Wu 0001
• Hong Wang
• Zexiang Li 0001
• Yunjiang Lou
• Jinbo Shi

In this paper, we identify a class of structurally distinguished machines, called quotient kinematics machines (QKM). A QKM realizes a motion task, typically characterized by a subgroup G of rigid transformation group SE(3), through coordinated motion of two mechanisms called modules. One is referred to as a subgroup module H and the other a complementary or quotient module G/H of H in G. Since QKM can retain both large workspace/rotation range of SKMs and speed/accuracy of PKMs by appropriate choice of modules, it is often implemented in high end machine design for semiconductor die/wire-bonding and 5-axis machining, etc. To promote QKM technology beyond occasional studies and applications, we use differential geometric techniques to develop a rigorous and precise treatment of QKMs, including: (i) modeling and analysis of QKMs; (ii) classification and synthesis of QKMs; (iii) PKM realization of quotient modules.

ICRA Conference 2007 Conference Paper

Accuracy Analysis of General Parallel Manipulators with Joint Clearance

• Jian Meng
• Dongjun Zhang
• Tinghua Zhang
• Hong Wang
• Zexiang Li 0001

Due to the joint clearance, parallel manipulators always exhibit some position and orientation errors at the mobile platform. This paper aims to provide a systematic framework for the error analysis problem of general parallel mechanisms influenced by the joint clearance. A novel and efficient method is proposed to evaluate the maximal pose errors of general spatial parallel manipulators with joint clearance.

ICRA Conference 2007 Conference Paper

Force Analysis of Whole Hand Grasp by Multifingered Robotic Hand

• Jijie Xu
• Michael Yu Wang
• Hong Wang
• Zexiang Li 0001

Under a whole hand grasp, it may not be possible to generate grasping forces in all directions. Thus, the traditional techniques developed based on fingertip contacts is inadequate. In this paper, we decompose the contact force space into four orthogonal subspaces, each with a clear physical interpretation. Based on linear matrix inequalities (LMI's) representations of grasping constraints, we address and formulate the active force closure and the active grasp feasibility problems as LMI feasibility problems. Combining the effects of both active and passive forces, we propose a new cost index for the whole hand grasping force optimization problem. We further simply the force optimization problem for a whole hand grasp, which is active force closure.

YNIMG Journal 2007 Journal Article

MR diffusion changes correlate with ultra-structurally defined axonal degeneration in murine optic nerve

• Qizhu Wu
• Helmut Butzkueven
• Melissa Gresle
• Frank Kirchhoff
• Anna Friedhuber
• Qing Yang
• Hong Wang
• Ke Fang

Diffusion weighted imaging (DWI) and diffusion tensor imaging (DTI) are widely used to investigate central nervous system (CNS) white matter structure and pathology. Changes in principal diffusivities parallel and perpendicular to nerve fibers or axonal tracts have been associated with axonal pathology and de/dysmyelination respectively. However, the ultra-structural properties and the pathological alterations of white matter responsible for diffusivity changes have not been fully elucidated. We examined the relationship between the directional diffusivities and ultra-structural properties in mouse optic nerve using healthy animals, and mice with optic neuritis (ON) that exhibited marked inflammatory changes and moderately severe axonal pathology. Progressive axonal degeneration in ON resulted in a 23% reduction of parallel diffusivity as detected by diffusion MRI (P <10−5), but no change in perpendicular diffusivity. Parallel diffusion changes were highly correlated with the total axolemmal cross-sectional area in the pre-chiasmal portion of the optic nerve (r =0. 86, P <0. 001). This study provides quantitative evidence that reduced parallel diffusivity in the optic nerve correlates significantly with axolemmal cross-sectional area reductions. MRI-based assessment of axonal degeneration in murine ON is feasible and potentially useful for monitoring of neuro-protective therapies in preclinical trials in animals.

YNIMG Journal 2001 Journal Article

A simulation of the effects of global normalization techniques in fMRI

• Maria Gavrilescu
• Marnie Shaw
• Peter Eckersley
• Imants Svalbe
• Hong Wang
• Gary F. Egan

YNIMG Journal 2001 Journal Article

Selective attention for motor action: An fMRI study

• Heidi Chapman
• Maria Gavrilescu
• Hong Wang
• Michael Kean
• Gary F. Egan
• Umberto Castiello