Arrow Research search

Author name cluster

Yun Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

27 papers
2 author rows

Possible papers

27

AAAI Conference 2026 Conference Paper

M2FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting

  • Yaohui Huang
  • Runmin Zou
  • Yun Wang
  • Laeeq Aslam
  • Ruipeng Dong

Forecasting time series with extreme events is critical yet challenging due to their high variance, irregular dynamics, and sparse but high-impact nature. While existing methods excel in modeling dominant regular patterns, their performance degrades significantly during extreme events, constituting the primary source of forecasting errors in real-world applications. Although some approaches incorporate auxiliary signals to improve performance, they still fail to capture extreme events' complex temporal dynamics. To address these limitations, we propose M²FMoE, an extreme-adaptive forecasting model that learns both regular and extreme patterns through multi-resolution and multi-view frequency modeling. It comprises three modules: (1) a multi-view frequency mixture-of-experts module assigns experts to distinct spectral bands in Fourier and Wavelet domains, with cross-view shared band splitter aligning frequency partitions and enabling inter-expert collaboration to capture both dominant and rare fluctuations; (2) a multi-resolution adaptive fusion module that hierarchically aggregates frequency features from coarse to fine resolutions, enhancing sensitivity to both short-term variations and sudden changes; (3) a temporal gating integration module that dynamically balances long-term trends and short-term frequency-aware features, improving adaptability to both regular and extreme temporal patterns. Experiments on real-world hydrological datasets with extreme patterns demonstrate that M²FMoE outperforms state-of-the-art baselines without requiring extreme-event labels.

PDF Details DOI

AAAI Conference 2026 Conference Paper

RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation

  • Run Ling
  • Wenji Wang
  • Yuting Liu
  • Guibing Guo
  • Haowei Liu
  • Jian Lu
  • Quanwei Zhang
  • Yexing Xu

Personalized image generation is crucial for improving the user experience, as it renders reference images into preferred ones according to user visual preferences. Although effective, existing methods face two main issues. First, existing methods treat all items in the user's historical sequence equally when extracting user preferences, overlooking the varying semantic similarities between historical items and the reference item. Disproportionately high weights for low-similarity items distort user visual preferences for the reference item. Second, existing methods heavily rely on consistency between generated and reference images to optimize generation, which leads to underfitting user preferences and hinders personalization. To address these issues, we propose Retrieval Augmented Personalized Image GenerAtion guided by Recommendation (RAGAR). Our approach uses a retrieval mechanism to assign different weights to historical items according to their similarities to the reference item, thereby extracting more refined users' visual preferences for the reference item. Then we introduce a novel rank task based on the multi-modal ranking model to optimize the personalization of the generated images instead of forcing depend on consistency. Extensive experiments and human evaluations on three real-world datasets demonstrate that RAGAR achieves significant improvements in both personalization and semantic metrics compared to five baselines.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Diff-LMM: Diffusion Teacher-Guided Spatio-Temporal Perception for Video Large Multimodal Models

  • Jisheng Dang
  • Ligen Chen
  • Jingze Wu
  • Ronghao Lin
  • Bimei Wang
  • Yun Wang
  • Liting Wang
  • Nannan Zhu

Dynamic spatio-temporal understanding is essential for video-based multimodal tasks, yet existing methods often struggle to capture fine-grained temporal and spatial relationships in long videos. Current approaches primarily rely on pre-trained CLIP encoders, which excel in semantic understanding but lack spatially-aware visual context. This leads to hallucinated results when interpreting fine-grained objects or scenes. To address these limitations, we propose a novel framework that integrates diffusion models into multimodal video models. By employing diffusion encoders at intermediate layers, we enhance visual representations through feature alignment and knowledge distillation losses, significantly improving the model's ability to capture spatial patterns over time. Additionally, we introduce a multi-level alignment strategy to learn robust feature correspondence from pre-trained diffusion models. Extensive experiments on benchmark datasets demonstrate our approach's state-of-the-art performance across multiple video understanding tasks. These results establish diffusion models as a powerful tool for enhancing multimodal video models in complex, dynamic scenarios.

PDF Details DOI

AAAI Conference 2025 Conference Paper

DualNet: Robust Self-Supervised Stereo Matching with Pseudo-Label Supervision

  • Yun Wang
  • Jiahao Zheng
  • Chenghao Zhang
  • Zhanjie Zhang
  • Kunhong Li
  • Yongjian Zhang
  • Junjie Hu

Self-supervised stereo matching has drawn attention due to its ability to estimate disparity without needing ground-truth data. However, existing self-supervised stereo matching methods heavily rely on the photo-metric consistency assumption, which is vulnerable to natural disturbances, resulting in ambiguous supervision and inferior performance compared to the supervised ones. To relax the limitation of the photo-metric consistency assumption and even bypass this assumption, we propose a novel self-supervised framework named DualNet, which consists of two key steps: robust self-supervised teacher learning and pseudo-label supervised student training. Specifically, the teacher model is first trained in a self-supervised manner with a focus on feature-metric consistency and data augmentation consistency. Then, the output of the teacher model is geometrically constrained to obtain high-quality pseudo labels. Benefiting from these high-quality pseudo labels, the student model can outperform its teacher model by a large margin. With the two well-designed steps, the proposed framework DualNet ranks 1st among all self-supervised methods on multiple benchmarks, surprisingly even outperforming several supervised counterparts.

PDF Details DOI

YNICL Journal 2025 Journal Article

Effects of individualized rTMS on functional connectivity related to the default mode network and frontal-parietal network in major depressive disorder: exploratory analysis of a randomized controlled trial

  • Jing Jin
  • Yun Wang
  • Sixiang Liang
  • Qingchen Fan
  • Meiling Li
  • Ling Zhang
  • Yanxiang Cao
  • Zhimin Wang

OBJECTIVE: Repetitive transcranial magnetic stimulation (rTMS) has been shown to alleviate depressive and anxiety symptoms in patients with major depressive disorder (MDD), typically by targeting the dorsolateral (DLPFC) or dorsomedial prefrontal cortex (DMPFC). Based on a pre-registered randomized controlled trial, this study presents an exploratory neuroimaging analysis investigating the impact of rTMS targeting the DLPFC versus the DMPFC on functional connectivity with the default mode network (DMN) and frontal-parietal network (FPN) in patients with MDD. METHODS: Sixty-four MDD patients were randomly assigned to DLPFC-rTMS (n = 36) or DMPFC-rTMS (n = 28) groups for a 21-day intervention. Symptoms were evaluated with Hamilton Depression Rating Scale (HAMD) and Hamilton Anxiety Rating Scale (HAMA). Changes in individualized functional connectivity (inFC) between individualized targets and DMN/FPN were assessed and correlated with symptom improvements. As a control analysis, FC was evaluated based on the group-based seeds of DLPFC or DMPFC. Additionally, symptom-specific circuit map comparisons were conducted. RESULTS: Both groups showed symptom improvements and changes in inFC with the DMN and FPN, but the specific connectivity profiles differ. In the DMN, the DLPFC-rTMS group showed decreased negative connectivity between left DLPFC and precuneus (t = -2.39, p = 0.022), while the DMPFC-rTMS group showed increased positive inFC between DMPFC and precuneus (t = -2.78, p = 0.01, FDR adjusted p = 0.034) and PCC (t = -3.15, p = 0.004, FDR adjusted p = 0.028). In the FPN, the DLPFC group showed decreased negative inFC with medial superior frontal gyrus (t = -2.35, p = 0.024) and decreased positive inFC with inferior parietal lobule (t = 2.3, p = 0.028). The DMPFC group showed increased positive connectivity with inferior frontal gyrus (t = -3.65, p = 0.001, FDR adjusted p = 0.019) and su pplementary motor area (t = -2.24, p = 0.033), and decreased negative connectivity with middle cingulate cortex (t = 2.27, p = 0.032). Canonical correlation analysis revealed a strong association between inFC changes and depression symptom improvement in the DMPFC-rTMS group (r = 0.57). Group seed-based FC changes were limited to the FPN and correlated with depressive improvement in the DLPFC-rTMS group (r = 0.52). Symptom-specific circuit maps linked to depression and anxiety were consistent across targets. CONCLUSION: Both DLPFC and DMPFC rTMS alleviate depressive and anxiety symptoms, displaying similar overall circuit patterns but distinct connectivity changes specific to their targets.

Details DOI

EAAI Journal 2025 Journal Article

Enhancing probabilistic photovoltaic power forecasting with parallel feature interaction and bayesian correction

  • Yun Wang
  • Guang Wu
  • Fan Zhang
  • Runmin Zou
  • Jie Wan

Photovoltaic power forecasting holds significant importance for solar energy grid integration and real-time dispatching in power systems. However, existing models struggle to extract sufficiently effective features and photovoltaic power is highly dependent on weather conditions, posing two major challenges in forecasting: the underutilization of features and the difficulty of forecasting under weather uncertainty. To address these challenges, this study proposes a parallel interactive deep evidential regression with Bayesian uncertainty correction model to enhance the accuracy of photovoltaic power forecasts. The proposed model incorporates a parallel feature interaction module that employs a bidirectional flow feature extraction, followed by an attention free mechanism, addressing feature underutilization in photovoltaic power forecasting. Additionally, the deep evidential regression module is introduced to capture the heavy-tailed characteristics of photovoltaic power by using the Student's t-distribution, enabling the estimation of both epistemic and aleatoric uncertainties. Since high weather uncertainty leads to high aleatoric uncertainty. Therefore, to mitigate weather uncertainty, a Bayesian weather uncertainty correction module is designed to adjust results exceeding a certain aleatoric uncertainty threshold with outputs from a Bayesian linear regression model trained on weather-excluded variables. The effectiveness of the proposed model is demonstrated through experiments conducted in Australia across four seasons, encompassing both deterministic forecasts and probabilistic forecasts. The performance of models is validated through comparisons with nine other models and the Diebold-Mariano test, confirming its efficacy in both deterministic and probabilistic photovoltaic power forecasting.

Details DOI

EAAI Journal 2025 Journal Article

Fault diagnosis of multi-unit nonlinear industrial processes based on a global–local attention convolutional neural network

  • Xueqin Yang
  • Yun Wang
  • Lijuan Qian
  • Gangyue Ye
  • Weirong Ye
  • Yuchen He

Recently, fault diagnosis technology has attracted much attention in multi-unit nonlinear industrial processes, which are composed of multiple interconnected subunits, with their complexity arising from nonlinear coupling relationships among these units. Unfortunately, existing fault diagnosis models have not well balanced the influence between inner-unit and cross-unit information. To address the above problem, a global–local attention convolutional neural network (GLACNN) method is proposed to improve the accuracy and interpretation of fault diagnosis results. Firstly, two special one-dimensional convolution kernels are designed to extract global features from the whole system. Secondly, local features from different units are derived in parallel approaches. Then, the corresponding global and local features are stacked to obtain the fusion features. The contribution of each unit to fault diagnosis will be assigned a proper weight through a channel attention module, which represents the local and global significance of different features in each unit. The efficacy of the proposed method is validated through its application in the Tennessee Eastman (TE) process and the penicillin production fermentation process.

Details DOI

AAAI Conference 2025 Conference Paper

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation

  • Min Lin
  • Gangwei Xu
  • Yun Wang
  • Xianqi Wang
  • Xin Yang

Scene flow methods based on deep learning have achieved impressive performance. However, current top-performing methods still struggle with ill-posed regions, such as extensive flat regions or occlusions, due to insufficient local evidence. In this paper, we propose a novel global-aware scene flow estimation network with global motion propagation, named FlowMamba. The core idea of FlowMamba is a novel Iterative Unit based on the State Space Model (ISU), which first propagates global motion patterns and then adaptively integrates the global motion information with previously hidden states. As the irregular nature of point clouds limits the performance of ISU in global motion propagation, we propose a feature-induced ordering strategy (FIO). The FIO leverages semantic-related and motion-related features to order points into a sequence characterized by spatial continuity. Extensive experiments demonstrate the effectiveness of FlowMamba, with 21.9% and 20.5% EPE3D reduction from the best published results on FlyingThings3D and KITTI datasets. Specifically, our FlowMamba is the first method to achieve millimeter-level prediction accuracy in FlyingThings3D and KITTI. Furthermore, the proposed ISU can be seamlessly embedded into existing iterative networks as a plug-and-play module, improving their estimation accuracy significantly.

PDF Details DOI

IROS Conference 2025 Conference Paper

Learning-Based Motion Controller for Reconfigurable Microswarms

  • Yamei Li
  • Yunxi Tang
  • Yun Wang
  • Yangmin Li 0001
  • Lidong Yang

Motion control of magnetic microswarms has attracted extensive attention due to its significance in microrobots-based biomedical applications such as targeted drug delivery. However, such reconfigurable microswarms are subject to complex interactions between individuals and environments which make accurate modeling challenging. These complexities of microswarms poses challenges for precise motion control, as traditional controllers often rely on precise mathematical models and manual parameter tuning that limits their scalability and efficiency. Learning-based methods, such as Deep Reinforcement Learning (DRL), offer an alternative but require large datasets (usually on the order of millions) and extensive exploration which may cause the microswarms instability in physical environments due to unreasonable actions during early training therefore results in the sim-to-real gap. Moreover, traditional DRL focuses on instantaneous state-action mappings, neglecting the sequential dependencies critical for accurate motion control, leading to low tracking accuracy in complex scenarios. To address these challenges, we propose a Learning from Demonstration (LfD)-based motion control framework, which inherently encode compensatory behaviors and task-specific adaptability into neural networks, enabling adaptive performance even under unmodeled disturbances. Furthermore, the neural networks consider a time series of microswarm states to determine the future control actions, enabling the system to learn sequential dependencies and transitions between states so as to ensure smooth and accurate motion control. Simulations and comparative experiments validate our framework’s effectiveness and demonstrate superior control accuracy and adaptability to microswarm’s shape changes.

Details

YNICL Journal 2025 Journal Article

Role of baseline resting-state functional connectivity of the nucleus accumbens subregions in antidepressant treatment in major depressive disorder

  • Yun Wang
  • Jingjing Zhou
  • Xiongying Chen
  • Rui Liu
  • Zhifang Zhang
  • Yuan Feng
  • Yuan Zhou
  • Gang Wang

The nucleus accumbens (NAc) plays a crucial role in the pathophysiology of major depressive disorder (MDD), and abnormal resting-state functional connectivity (rsFC) of NAc subregions has been found in MDD. However, it is unclear whether the altered rsFC of NAc subregions can predict the efficacy of antidepressant treatment, and whether antidepressants are capable of restoring the altered rsFC of NAc subregions in MDD. The purpose of this study was to investigate the role of rsFC of the NAc subregions in antidepressant treatment for MDD. Resting-state functional magnetic resonance imaging (fMRI) data were collected from 46 unmedicated MDD patients at baseline and after 12 weeks of escitalopram treatment, along with fMRI data from 58 healthy controls (HCs). We examined group differences in rsFC of the NAc subregions between MDD patients and HCs, explored whether the altered rsFC at baseline was associated with treatment efficacy, and evaluated whether antidepressant treatment could normalize rsFC abnormalities in the NAc subregions in MDD. Compared to HCs, MDD patients exhibited decreased rsFC between the NAc subregions and the middle cingulate cortex (MCC). Lower levels of rsFC between the NAc subregions and the MCC at baseline predicted greater improvement in depressive symptoms. Furthermore, rsFC between the NAc subregions and the MCC increased following antidepressant treatment in MDD. Our findings suggest that rsFC alterations between the NAc subregions and the MCC may serve as a potential biomarker for predicting antidepressant treatment efficacy, and that dysfunction in the frontal-ventral striatum circuitry may represent a key therapeutic target for MDD.

Details DOI

EAAI Journal 2025 Journal Article

Towards salient object detection via parallel dual-decoder network

  • Chaojun Cen
  • Fei Li
  • Zhenbo Li
  • Yun Wang

Salient object detection, an important preprocessing step in computer vision, segments the most prominent objects in an image. However, existing research in this field utilizes transformer-based methods to capture global context information, failing to effectively obtain local spatial features. To solve this issue, we propose a parallel dual-decoder network, which consists of a novel semantic decoder and a modified salient decoder. Specifically, the proposed semantic decoder is designed to learn the local spatial details, and the salient decoder utilizes the learnable queries to establish global saliency dependencies among objects. Moreover, the two decoders establish correlations between saliency and multi-scale semantic representations through cross-attention interaction, significantly enhancing the performance of salient object detection. In other words, we obtain global context information in the decoder to prevent discriminative features from being diluted during information propagation. Extensive experiments on 15 benchmark datasets demonstrate that our model significantly outperforms other comparison methods and shows promising potential for real-world applications such as challenging optical remote sensing, underwater, low-light, and other open scenarios. In addition, our method shows excellent performance in other downstream tasks such as camouflaged object detection, transparent object detection, shadow detection, and semantic segmentation.

Details DOI

EAAI Journal 2025 Journal Article

VectorSketcher: Learning to create a vector-based free-hand sketch

  • Zhanjie Zhang
  • Quanwei Zhang
  • Junsheng Luan
  • Mengyuan Yang
  • Yun Wang
  • Lei Zhao

Sketch synthesis refers to converting a given content image into a sketch. Existing sketch synthesis methods are generally divided into pixel-based and vector-based sketch synthesis. Pixel-based sketch synthesis methods always introduce obvious artifacts and disharmonious patterns. Besides, they cannot support generating sketches with different levels of abstraction. The vector-based sketch synthesis methods have limitations in describing the structure and semantics of the content image. To tackle these problems, we propose a novel framework called VectorSketcher, which can create vectorized sketches that accurately describe the structure and semantics of the content images without introducing obvious artifacts and disharmonious patterns. Specifically, we proposed a Multi-scale Feature-based Stroke Initialization (MFSI) to speed up the optimization and essential visual details of the given image. We introduce a Controllable Score Distillation Sampling loss (CSDS) to further learn the content image’s detail. Extensive quantitative and qualitative experiments show that VectorSketcher can generate more accurate vector-based sketches than existing state-of-the-art (SOTA) sketch synthesis methods.

Details DOI

TMLR Journal 2025 Journal Article

ViTime: Foundation Model for Time Series Forecasting Powered by Vision Intelligence

  • Luoxiao Yang
  • Yun Wang
  • Xinqi Fan
  • Israel Cohen
  • Jingdong Chen
  • Zijun Zhang

Time series forecasting (TSF) possesses great practical values in various fields, including power and energy, transportation, etc. TSF methods have been studied based on kncowledge from classical statistics to modern deep learning. Yet, all of them were developed based on one fundamental concept, the numerical data fitting. Thus, the models developed have been long known for being problem-specific and lacking application generalizability. Practitioners expect a TSF foundation model that serves TSF tasks in different applications. The central question is then how to develop such a TSF foundation model. This paper offers one pioneering study in the TSF foundation model development method and proposes a vision intelligence-powered framework, ViTime, for the first time. ViTime fundamentally shifts TSF from numerical fitting to operations based on a binary image-based time series metric space and naturally supports both point and probabilistic forecasting. We also provide rigorous theoretical analyses of ViTime, including quantization-induced system error bounds and principled strategies for optimal parameter selection. Furthermore, we propose RealTS, an innovative synthesis algorithm generating diverse and realistic training samples, effectively enriching the training data and significantly enhancing model generalizability. Extensive experiments demonstrate ViTime's SOTA performance. In zero-shot scenarios, ViTime outperforms TimesFM by 9-15%. With just 10% fine-tuning data, ViTime surpasses both leading foundation models and fully-supervised benchmarks, a gap that widens with 100% fine-tuning. ViTime also exhibits exceptional robustness, effectively handling missing data and outperforming TimesFM by 20-30% under various data perturbations, validating the power of its visual space data operation paradigm.

PDF Details

ICRA Conference 2024 Conference Paper

Research on bionic foldable wing for flapping wing micro air vehicle

  • Shengjie Xiao
  • Kai Hu 0004
  • Yuhong Sun
  • Yun Wang
  • Bo Qin
  • Huichao Deng
  • Xuan Wu
  • Xilun Ding

This paper presents a bionic foldable wing that imitates the hind wing of ladybirds. Based on the folding mechanism of the hind wing of ladybirds and the theory of origami, the motion model of the bionic foldable wing is established, yield the motion law of the crease angles and the variation relationship between the panels are obtained. Bionic foldable wings utilise shape memory alloy to drive wings to fold, and embedded torsion springs to release energy to realize the function of wing unfolding. In the experiments of the vehicle equipped with foldable wings, the lift and attitude torque of bionic foldable wings are measured by the F/T sensor. The experimental results indicated that its aerodynamic performance is basically close to that of our optimized non-foldable wings. Moreover, the vehicle with foldable wings has been able to overcome gravity to achieve flight, which provides a novel concept for the research on flapping wing.

Details

EAAI Journal 2022 Journal Article

A dual attribute weighted decision fusion system for fault classification based on an extended analytic hierarchy process

  • Yuchen He
  • Ruichong Lou
  • Yun Wang
  • Jun Wang
  • Xinyun Fang

As substantial parts of process monitoring, fault classification techniques have been widely utilized in modern industries. However, most methods can only perform well under specific condition, which indicates that it is always difficult to ensure the classification efficiency for complex industrial processes using only one method. In this paper a weighted decision fusion system is proposed where an extended analytic hierarchy process (EAHP) structure is designed to give a comprehensive explanation for the weights assigned to the original fault classification results. Firstly, the fault category information is embedded in the EAHP structure, which makes it possible to consider both fault-wise and classifier-wise information in the fault classification. Secondly, an overall priority (OP) matrix is proposed to provide full prior knowledge for all classifiers. Different from previous researches, traditional OP vectors are replaced by the new-designed OP matrix which can contain more information about fault category. Thirdly, another confidence matrix is carried out to update the classification results. Compared with previous state-of-art, the confidence matrix can be adjusted according to the specific original classification result Finally, the effectiveness of the proposed method is verified by a numerical example and the Tennessee Eastman process (TEP) where the proposed decision fusion system shows superior fault classification results in both experiments.

Details DOI

YNICL Journal 2022 Journal Article

Altered frequency-specific/universal amplitude characteristics of spontaneous brain oscillations in patients with bipolar disorder

  • Zhi-Fang Zhang
  • Qi-Jing Bo
  • Feng Li
  • Lei Zhao
  • Peng Gao
  • Yun Wang
  • Rui Liu
  • Xiong-Ying Chen

The human brain is a dynamic system with intrinsic oscillations in spontaneous neural activity. Whether the dynamic characteristics of these spontaneous oscillations are differentially altered across different frequency bands in patients with bipolar disorder (BD) remains unclear. This study recruited 65 patients with BD and 85 healthy controls (HCs). The entire frequency range of resting-state fMRI data was decomposed into four frequency intervals. Two-way repeated-measures ANCOVA was employed to detect frequency-specific/universal alterations in the dynamic oscillation amplitude in BD. The patients were then divided into two subgroups according to their mood states to explore whether these alterations were independent of their mood states. Finally, other window sizes, step sizes, and window types were tested to replicate all analyses. Frequency-specific abnormality of the dynamic oscillation amplitude was detected within the posterior medial parietal cortex (centered at the precuneus extending to the posterior cingulate cortex). This specific profile indicates decreased amplitudes in the lower frequency bands (slow-5/4) and no amplitude changes in the higher frequency bands (slow-3/2) compared with HCs. Frequency-universal abnormalities of the dynamic oscillation amplitude were also detectable, indicating increased amplitudes in the thalamus and left cerebellum anterior lobe but decreased amplitudes in the medial superior frontal gyrus. These alterations were independent of the patients' mood states and replicable across multiple analytic and parametric settings. In short, frequency-specific/universal amplitude characteristics of spontaneous oscillations were observed in patients with BD. These abnormal characteristics have important implications for specific functional changes in BD from multiple frequency and dynamic perspectives.

Details DOI

EAAI Journal 2022 Journal Article

Towards fusing fuzzy discriminative projection and representation learning for image classification

  • Yun Wang
  • Zhenbo Li
  • Fei Li
  • Pu Yang
  • Jun Yue

The fuzzy and indistinguishable data affected by complex and variable factors lead to the inferior recognition performance, which is hard to avoid in data acquisition. Subspace projection is widely used in extracting low-dimensional important features for image processing task. However, many existing methods rarely explore on the fuzziness and uncertainty of visual data, while lack sufficient mining of prior knowledge. In this work, we propose a novel fuzzy discriminative projection and representation learning (FDPR) method for image classification. Specifically, the fuzzy weight matrix with label information is designed in the data reconstruction to generate more specific sparse constraint on representation coefficients. In addition, low-rank and l 2, 1 norm constraints are introduced to enhance the robustness of the algorithm. Finally, we combine a classification regression term with the representation coefficients carrying discriminative information for the subspace projection learning, thus fully utilizing data label information and eventually benefiting the subspace to be more distinguishable. The experimental results on several datasets show that our proposed model performs well with effectiveness and robustness surpassing other state-of-the-art approaches.

Details DOI

YNICL Journal 2021 Journal Article

Anhedonia correlates with functional connectivity of the nucleus accumbens subregions in patients with major depressive disorder

  • Rui Liu
  • Yun Wang
  • Xiongying Chen
  • Zhifang Zhang
  • Le Xiao
  • Yuan Zhou

BACKGROUND: The nucleus accumbens (NAc) is an important region in reward circuit that has been linked with anhedonia, which is a characteristic symptom of major depressive disorder (MDD). However, the relationship between the functional connectivity of the NAc subregions and anhedonia in MDD patients remains unclear. METHODS: We acquired resting-state functional magnetic resonance imaging (fMRI) scans from fifty-one subjects (23 MDD patients and 28 healthy controls). We assessed subjects' trait anhedonia with the Temporal Experience of Pleasure Scale (TEPS). Seed-based resting-state functional connectivity (rsFC) was conducted for each of the NAc subregions (bilateral core-like and shell-like subdivisions) separately to identify regions whose rsFCs with the NAc subregions were altered in the MDD patients and regions whose rsFCs with the NAc subregions showed different correlates with anhedonia between the MDD patients and the healthy controls. RESULTS: Compared with the health controls, the MDD patients showed decreased rsFCs of the right NAc core-like subdivision with the left mid-anterior orbital prefrontal cortex and the right inferior parietal lobe as well as decreased rsFC of the left NAc core-like subdivision with the right middle frontal gyrus. Moreover, the severity of anhedonia by the group interaction was significant for the rsFC of the right NAc shell-like subdivision with the subgenual/pregenual anterior cingulate cortex and the rsFC of the right NAc core-like subdivision with the precuneus. CONCLUSIONS: We found that the neural correlates of anhedonia indicated by the rsFCs of the NAc subregions were modulated by depression. The modulation effect was regionally-dependent. These findings enrich our understanding of the neural basis of anhedonia in MDD.

Details DOI

AAAI Conference 2021 Conference Paper

Deep Wasserstein Graph Discriminant Learning for Graph Classification

  • Tong Zhang
  • Yun Wang
  • Zhen Cui
  • Chuanwei Zhou
  • Baoliang Cui
  • Haikuan Huang
  • Jian Yang

Graph topological structures are crucial to distinguish different-class graphs. In this work, we propose a deep Wasserstein graph discriminant learning (WGDL) framework to learn discriminative embeddings of graphs in Wassersteinmetric (W-metric) matching space. In order to bypass the calculation of W-metric class centers in discriminant analysis, as well as better support batch process learning, we introduce a reference set of graphs (aka graph dictionary) to express those representative graph samples (aka dictionary keys). On the bridge of graph dictionary, every input graph can be projected into the latent dictionary space through our proposed Wasserstein graph transformation (WGT). In WGT, we formulate inter-graph distance in W-metric space by virtue of the optimal transport (OT) principle, which effectively expresses the correlations of cross-graph structures. To make WGDL better representation ability, we dynamically update graph dictionary during training by maximizing the Wasserstein Discriminant loss, i. e. the ratio of inter-class versus intra-class Wasserstein distance. To evaluate our WGDL method, comprehensive experiments are conducted on six graph classification datasets. Experimental results demonstrate the effectiveness of our WGDL, and state-of-the-art performance.

PDF Details

YNIMG Journal 2021 Journal Article

Intra-session test-retest reliability of functional connectivity in infants

  • Yun Wang
  • Walter Hinds
  • Cristiane S Duarte
  • Seonjoo Lee
  • Catherine Monk
  • Melanie Wall
  • Glorisa Canino
  • Ana Carolina C. Milani

Resting functional MRI studies of the infant brain are increasingly becoming an important tool in developmental neuroscience. Whereas the test-retest reliability of functional connectivity (FC) measures derived from resting fMRI data have been characterized in the adult and child brain, similar assessments have not been conducted in infants. In this study, we examined the intra-session test-retest reliability of FC measures from 119 infant brain MRI scans from four neurodevelopmental studies. We investigated edge-level and subject-level reliability within one MRI session (between and within runs) measured by the Intraclass correlation coefficient (ICC). First, using an atlas-based approach, we examined whole-brain connectivity as well as connectivity within two common resting fMRI networks - the default mode network (DMN) and the sensorimotor network (SMN). Second, we examined the influence of run duration, study site, and scanning manufacturer (e.g., Philips and General Electric) on ICCs. Lastly, we tested spatial similarity using the Jaccard Index from networks derived from independent component analysis (ICA). Consistent with resting fMRI studies from adults, our findings indicated poor edge-level reliability (ICC = 0.14-0.18), but moderate-to-good subject-level intra-session reliability for whole-brain, DMN, and SMN connectivity (ICC = 0.40-0.78). We also found significant effects of run duration, site, and scanning manufacturer on reliability estimates. Some ICA-derived networks showed strong spatial reproducibility (e.g., DMN, SMN, and Visual Network), and were labelled based on their spatial similarity to analogous networks measured in adults. These networks were reproducibly found across different study sites. However, other ICA-networks (e.g. Executive Control Network) did not show strong spatial reproducibility, suggesting that the reliability and/or maturational course of functional connectivity may vary by network. In sum, our findings suggest that developmental scientists may be on safe ground examining the functional organization of some major neural networks (e.g. DMN and SMN), but judicious interpretation of functional connectivity is essential to its ongoing success.

Details DOI

YNIMG Journal 2021 Journal Article

Spatiotemporal characterisation of ischaemic lesions in transient stroke animal models using diffusion free water elimination and mapping MRI with echo time dependence

  • Ezequiel Farrher
  • Chia-Wen Chiang
  • Kuan-Hung Cho
  • Farida Grinberg
  • Richard P. Buschbeck
  • Ming-Jye Chen
  • Kuo-Jen Wu
  • Yun Wang

BACKGROUND AND PURPOSE: The excess fluid as a result of vasogenic oedema and the subsequent tissue cavitation obscure the microstructural characterisation of ischaemic tissue by conventional diffusion and relaxometry MRI. They lead to a pseudo-normalisation of the water diffusivity and transverse relaxation time maps in the subacute and chronic phases of stroke. Within the context of diffusion MRI, the free water elimination and mapping method (FWE) with echo time dependence has been proposed as a promising approach to measure the amount of free fluid in brain tissue robustly and to eliminate its biasing effect on other biomarkers. In this longitudinal study of transient middle cerebral artery occlusion (MCAo) in the rat brain, we investigated the use of FWE MRI with echo time dependence for the characterisation of the tissue microstructure and explored the potential of the free water fraction as a novel biomarker of ischaemic tissue condition. METHODS: Adult rats received a transient MCAo. Diffusion- and transverse relaxation-weighted MRI experiments were performed longitudinally, pre-occlusion and on days 1, 3, 4, 5, 6, 7 and 10 after MCAo on four rats. Histology was performed for non-stroke and 1, 3 and 10 days after MCAo on three different rats at each time point. RESULTS: The free water fraction was homogeneously increased in the ischaemic cortex one day after stroke. Between three and ten days after stroke, the core of the ischaemic tissue showed a progressive normalisation in the amount of free water, whereas the inner and outer border zones of the ischaemic cortex depicted a large, monotonous increase with time. The specific lesions in brain sections were verified by H&E and immunostaining. The tissue-specific diffusion and relaxometry MRI metrics in the ischaemic cortex were significantly different compared to their conventional counterpart. CONCLUSIONS: Our results demonstrate that the free water fraction in FWE MRI with echo time dependence is a valuable biomarker, sensitive to the progressive degeneration in ischaemic tissue. We showed that part of the heterogeneity previously observed in conventional parameter maps can be accounted for by a heterogeneous distribution of free water in the tissue. Our results suggest that the temporal evolution of the free fluid fraction map at the core and inner border zone can be associated with the pathological changes linked to the evolution of vasogenic oedema. Namely, the homogeneous increase in free water one day after stroke and its tendency to normalise in the core of the ischaemic cortex starting three days after stroke, followed by a progressive increase in free water at the inner border zone from three to ten days after stroke. Finally, the monotonous increase in free fluid in the outer border zone of the cortex reflects the formation of fluid-filled cysts.

Details DOI

YNICL Journal 2019 Journal Article

Diagnosis and prognosis of Alzheimer's disease using brain morphometry and white matter connectomes

  • Yun Wang
  • Chenxiao Xu
  • Ji-Hwan Park
  • Seonjoo Lee
  • Yaakov Stern
  • Shinjae Yoo
  • Jong Hun Kim
  • Hyoung Seop Kim

Accurate, reliable prediction of risk for Alzheimer's disease (AD) is essential for early, disease-modifying therapeutics. Multimodal MRI, such as structural and diffusion MRI, is likely to contain complementary information of neurodegenerative processes in AD. Here we tested the utility of the multimodal MRI (T1-weighted structure and diffusion MRI), combined with high-throughput brain phenotyping-morphometry and structural connectomics-and machine learning, as a diagnostic tool for AD. We used, firstly, a clinical cohort at a dementia clinic (National Health Insurance Service-Ilsan Hospital [NHIS-IH]; N = 211; 110 AD, 64 mild cognitive impairment [MCI], and 37 cognitively normal with subjective memory complaints [SMC]) to test the diagnostic models; and, secondly, Alzheimer's Disease Neuroimaging Initiative (ADNI)-2 to test the generalizability. Our machine learning models trained on the morphometric and connectome estimates (number of features = 34,646) showed optimal classification accuracy (AD/SMC: 97% accuracy, MCI/SMC: 83% accuracy; AD/MCI: 97% accuracy) in NHIS-IH cohort, outperforming a benchmark model (FLAIR-based white matter hyperintensity volumes). In ADNI-2 data, the combined connectome and morphometry model showed similar or superior accuracies (AD/HC: 96%; MCI/HC: 70%; AD/MCI: 75% accuracy) compared with the CSF biomarker model (t-tau, p-tau, and Amyloid β, and ratios). In predicting MCI to AD progression in a smaller cohort of ADNI-2 (n = 60), the morphometry model showed similar performance with 69% accuracy compared with CSF biomarker model with 70% accuracy. Our comparisons of the classifiers trained on structural MRI, diffusion MRI, FLAIR, and CSF biomarkers showed the promising utility of the white matter structural connectomes in classifying AD and MCI in addition to the widely used structural MRI-based morphometry, when combined with machine learning.

Details DOI

IJCAI Conference 2019 Conference Paper

Tag2Gauss: Learning Tag Representations via Gaussian Distribution in Tagged Networks

  • Yun Wang
  • Lun Du
  • Guojie Song
  • Xiaojun Ma
  • Lichen Jin
  • Wei Lin
  • Fei Sun

Keyword-based tags (referred to as tags) are used to represent additional attributes of nodes in addition to what is explicitly stated in their contents, like the hashtags in YouTube. Aside of being auxiliary information for node representation, tags can also be used for retrieval, recommendation, content organization, and event analysis. Therefore, tag representation learning is of great importance. However, to learn satisfactory tag representations is challenging because 1) traditional representation methods generally fail when it comes to representing tags, 2) bidirectional interactions between nodes and tags should be modeled, which are generally not dealt within existing research works. In this paper, we propose a tag representation learning model which takes tag-related node interaction into consideration, named Tag2Gauss. Specifically, since tags represent node communities with intricate overlapping relationships, we propose that Gaussian distributions would be appropriate in modeling tags. Considering the bidirectional interactions between nodes and tags, we propose a tag representation learning model mapping tags to distributions consisting of two embedding tasks, namely Tag-view embedding and Node-view embedding. Extensive evidence demonstrates the effectiveness of representing tag as a distribution, and the advantages of the proposed architecture in many applications, such as the node classification and the network visualization.

PDF Details

IJCAI Conference 2018 Conference Paper

Dynamic Network Embedding: An Extended Approach for Skip-gram based Network Embedding

  • Lun Du
  • Yun Wang
  • Guojie Song
  • Zhicong Lu
  • Junshan Wang

Network embedding, as an approach to learn low-dimensional representations of vertices, has been proved extremely useful in many applications. Lots of state-of-the-art network embedding methods based on Skip-gram framework are efficient and effective. However, these methods mainly focus on the static network embedding and cannot naturally generalize to the dynamic environment. In this paper, we propose a stable dynamic embedding framework with high efficiency. It is an extension for the Skip-gram based network embedding methods, which can keep the optimality of the objective in the Skip-gram based methods in theory. Our model can not only generalize to the new vertex representation, but also update the most affected original vertex representations during the evolvement of the network. Multi-class classification on three real-world networks demonstrates that, our model can update the vertex representations efficiently and achieve the performance of retraining simultaneously. Besides, the visualization experimental result illustrates that, our model is capable of avoiding the embedding space drifting.

PDF Details

IJCAI Conference 2018 Conference Paper

Galaxy Network Embedding: A Hierarchical Community Structure Preserving Approach

  • Lun Du
  • Zhicong Lu
  • Yun Wang
  • Guojie Song
  • Yiming Wang
  • Wei Chen

Network embedding is a method of learning a low-dimensional vector representation of network vertices under the condition of preserving different types of network properties. Previous studies mainly focus on preserving structural information of vertices at a particular scale, like neighbor information or community information, but cannot preserve the hierarchical community structure, which would enable the network to be easily analyzed at various scales. Inspired by the hierarchical structure of galaxies, we propose the Galaxy Network Embedding (GNE) model, which formulates an optimization problem with spherical constraints to describe the hierarchical community structure preserving network embedding. More specifically, we present an approach of embedding communities into a low dimensional spherical surface, the center of which represents the parent community they belong to. Our experiments reveal that the representations from GNE preserve the hierarchical community structure and show advantages in several applications such as vertex multi-class classification and network visualization. The source code of GNE is available online.

PDF Details

IS Journal 2015 Journal Article

Predicting Location-Based Sequential Purchasing Events by Using Spatial, Temporal, and Social Patterns

  • Yun Wang
  • Sudha Ram

Location-based sequential event prediction is an interesting problem with many real-world applications. For example, knowing when and where people will use certain kinds of services could enable the development of robust anticipatory systems. A key to this problem is in understanding the nature of the process from which sequential data arises. Usually, human behavior exhibits distinct spatial, temporal, and social patterns. The authors examine three kinds of patterns extracted from sequential purchasing events and propose a novel model that captures contextual dependencies in spatial sequence, customers' temporal preferences, and social influence via an implicit network. Their model outperforms existing models based on evaluations using a real-world dataset of smartcard transaction records from a large educational institution with 13, 753 students during a 10-month time period.

Details DOI

YNIMG Journal 2011 Journal Article

Post-treatment with amphetamine enhances reinnervation of the ipsilateral side cortex in stroke rats

  • Hua-Shan Liu
  • Hui Shen
  • Brandon K. Harvey
  • Priscila Castillo
  • Hanbing Lu
  • Yihong Yang
  • Yun Wang

Amphetamine (AM) treatment has been shown to alter behavioral recovery after ischemia caused by embolism, permanent unilateral occlusion of the common carotid and middle cerebral arteries, or unilateral sensorimotor cortex ablation in rats. However, the behavioral results are inconsistent possibly due to difficulty controlling the size of the lesion before treatment. There is also evidence that AM promotes neuroregeneration in the cortex contralateral to the infarction; however, the effects of AM in the ipsilateral cortex remain unclear. The purpose of this study was to employ T2-weighted imaging (T2WI) to establish controlled criteria for AM treatment and to examine neuroregenerative effects in both cortices after stroke. Adult rats were anesthetized, and the right middle cerebral artery was ligated for 90min to generate lesions in the ipsilateral cortex. Animals were separated into two equal treatment groups (AM or saline) according to the size of infarction, measured by T2WI at 2days after stroke. AM or saline was administered to stroke rats every third day starting on day 3 for 4weeks. AM treatment significantly reduced neurological deficits, as measured by body asymmetry and Bederson's score. T2WI and diffusion tensor imaging (DTI) were used to examine the size of infarction and axonal reinnervation, respectively, before and following treatment on days 2, 10 and 25 after stroke. AM treatment reduced the volume of tissue loss on days 10 and 25. A significant increase in fractional anisotropy ratio was found in the ipsilateral cortex after repeated AM administration, suggesting a possible increase in axonal outgrowth in the lesioned side cortex. Western analysis indicated that AM significantly increased the expression of synaptophysin ipsilaterally and neurofilament bilaterally. AM also enhanced matrix metalloproteinase (MMP) enzymatic activity, determined by MMP zymography in the lesioned side cortex. qRT-PCR was used to examine the expression of trophic factors after the 1st and 2nd doses of AM or saline injection. The expression of BDNF, but not BMP7 or CART, was significantly enhanced by AM in the lesioned side cortex. In conclusion, post-stroke treatment with AM facilitates behavioral recovery, which is associated with an increase in fractional anisotropy activity, enhanced fiber growth in tractography, synaptogenesis, upregulation of BDNF, and MMP activity mainly in the lesioned cortex. Our data suggest that the ipsilateral cortex may be the major target of action in stroke brain after AM treatment.

Details DOI
v2026.09.13