Author name cluster

Xiaojun Xu

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.

19 papers

2 author rows

YNICL Journal 2025 Journal Article

Arterial spin labeling MRI based perfusion pattern related to motor dysfunction and L-DOPA reactivity in Parkinson’s disease

Qianshi Zheng
Weijin Yuan
Jiaqi Wen
Jianmei Qin
Chenqing Wu
Haoting Wu
Xiaojie Duanmu
Sijia Tan

OBJECTIVE: Identifying intrinsic pattern of Parkinson's disease (PD) helps to better understand of PD and provide insights to disease identification and treatment monitoring. Here we confirmed the PD-related covariance pattern (PDRP) by using arterial spin labelling technology (ASL-PDRP) and explore its potential for predicting motor progression and levodopa (L-DOPA) reactivity reduction. METHODS: Data from an original cohort of 179 PD and 62 normal controls (NC) and a validation cohort including 36 PD and 19 NC to construct and validate the ASL-PDRP. The correlations between the pattern and motor symptoms were analyzed cross-sectionally and longitudinally (71 PD owned longitudinal data) with hierarchical linear regression analysis. Kaplan-Meier analysis was conducted in 54 L-DOPA-managed PD patients to predict the levodopa reactivity reduction. RESULTS: The first principal component was predominantly recognized as the ASL-PDRP, with its expression being higher in PD than NC in both sets (original: P = 0.017, AUC = 0.598; validation: P = 0.024, AUC = 0.661). The pattern expression was associated with UPDRS III (P = 0.006) and sub-symptoms (axial: P < 0.001; rigidity: P = 0.003; bradykinesia: P = 0.015) at baseline. The ASL-PDRP could predict the progression of UPDRS III (P = 0.021, β = 4.930). Higher expression of the pattern had slower rate of levodopa reactivity reduction in PD patients with axial symptom (P = 0.031). CONCLUSION: The identified ASL-PDRP may have potential for characterizing PD with the ability to predict motor progression and L-DOPA reactivity reduction.

Details DOI

ICML Conference 2025 Conference Paper

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

Han Zhong 0001
Yutong Yin
Shenao Zhang
Xiaojun Xu
Yuanxin Liu
Yifei Zuo
Zhihan Liu
Boyi Liu 0001

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, yet generating reliable reasoning processes remains a significant challenge. We present a unified probabilistic framework that formalizes LLM reasoning through a novel graphical model incorporating latent thinking processes and evaluation signals. Our framework addresses two critical questions: (1) how to generate high-quality reasoning processes during inference automatically, and (2) how to integrate these processes into post-training. We propose the Bootstrapping Reinforced Thinking Process (BRiTE) algorithm and demonstrate its theoretical convergence at a rate of $1/T$, where $T$ is the number of iterations. The algorithm operates in two steps. First, it generates high-quality rationales by approximating the desired posterior distribution using a reinforcement learning approach with a novel reward shaping mechanism. Second, it fine-tunes the base LLM by maximizing the joint probability of rationale generation with respect to LLM parameters. Empirical evaluation on GSM8K and MATH benchmarks demonstrates that our approach consistently improves performance across different model sizes without requiring human-annotated thinking processes, outperforming standard chain-of-thought prompting while enhancing existing post-training methods.

Details

YNIMG Journal 2025 Journal Article

Hippocampal subfields in aging: Sex-specific trajectories in structure and hemodynamics

Jiaqi Wen
Chenyang Li
Zhe Sun
Chao Wang
Jiangyang Zhang
Xiaojun Guan
Xiaojun Xu
Thomas Wisniewski

Sex differences in hippocampal aging have been increasingly recognized, with females showing greater vulnerability to neurodegeneration, particularly after menopause. However, the underlying neurobiological mechanisms remain unclear, especially at the level of hippocampal subfields. Leveraging high-resolution T1-, T2-weighted, and multi-delay arterial spin labeling MRI from 650 adults in the Human Connectome Project-Aging dataset, we examined sex-specific alterations in hippocampal subfield volume, arterial transit time (ATT), and cerebral blood flow (CBF) across the adult lifespan. All hippocampal subfields showed age-related atrophy and ATT prolongation. An age × sex interaction effect on ATT was observed in CA1 and CA2, indicating that age-related increases in ATT were more pronounced in females than in males in these subfields. Moreover, females exhibited more pronounced hippocampal subfields CBF reductions with aging and atrophy, while males showed relatively preserved CBF, with an increase in subiculum perfusion. Furthermore, CA1 showed the lowest perfusion and the strongest association with atrophy among hippocampal subfields. To investigate the potential impact of menopausal hormonal changes on sex-specific patterns, we explored the hypothalamic structure and hemodynamic alterations during aging and their effects on the hippocampus, given that hypothalamus regulates gonadal hormone secretion through the hypothalamic-pituitary-gonadal axis. We found significant hypothalamic atrophy during aging in both sexes, accompanied by ATT prolongation exclusively in females, which was associated with hippocampal atrophy and impaired hemodynamics. Our study highlights the intricate interplay between hippocampal structure and vascular function, revealing sex- and subfield-specific aging trajectories. These findings provide a normative quantitative imaging reference to age-related neurodegenerative diseases such as Alzheimer's Disease.

Details DOI

YNIMG Journal 2025 Journal Article

Motor-cognitive aging: The role of motor cortex and its pathways

Jiaqi Wen
Zifei Liang
Chenyang Li
Huize Pang
Li Jiang
Jiayi Li
Xiaojun Guan
Jiangyang Zhang

BACKGROUND: Motor and cognitive decline are hallmark features of aging. In the primary motor cortex (M1), pyramidal neurons project to the corticospinal tract (CST), a well-established motor pathway, and send collaterals to the ipsilateral striatum, forming the corticostriatal tract (CStrT). While the CST has been extensively studied, the role of the CStrT in motor and cognitive aging remains poorly understood. METHODS: We analyzed T1- and T2-weighted MRI, multi-delay arterial spin labeling, and multi-shell diffusion MRI data from 339 right-handed healthy adults (aged 36-90 years) in the Human Connectome Project-Aging dataset. Age-related trajectories of M1 structure and hemodynamics, as well as CST and CStrT microstructure, were assessed. Segment-wise along-tract analyses were conducted to identify localized tract degeneration. Mediation analyses were performed to examine whether tract integrity linked M1 atrophy to motor and cognitive performance. RESULTS: With age, M1 exhibited reduced volume and hemodynamics, altered T1/T2 ratio, and increased cortical curvature, reflecting structural and hemodynamic alterations. Along-tract analyses revealed localized microstructural degeneration in the CST adjacent to M1, whereas the CStrT showed more extensive degeneration along its trajectory. These tract changes were associated with structural and hemodynamic alterations in M1. Furthermore, integrity of the dominant (left) CST and CStrT mediated the relationship between ipsilateral M1 atrophy and motor decline. Notably, CStrT integrity also mediated the association between M1 atrophy and motor cognition decline. CONCLUSION: These findings establish age-related structural and functional degeneration of M1 and its pathways, highlighting the CStrT as a critical mediator between motor cortical atrophy and both motor and cognitive decline. These normative imaging markers of healthy aging may help inform the early detection of neurodegenerative diseases.

Details DOI

YNIMG Journal 2025 Journal Article

Robust computation of subcortical functional connectivity guided by quantitative susceptibility mapping: An application in Parkinson’s disease diagnosis

Jianmei Qin
Haoting Wu
Chenqing Wu
Tao Guo
Cheng Zhou
Xiaojie Duanmu
Sijia Tan
Jiaqi Wen

Previous resting state functional MRI (rs-fMRI) analyses of the basal ganglia in Parkinson's disease heavily relied on T1-weighted imaging (T1WI) atlases. However, subcortical structures are characterized by subtle contrast differences, making their accurate delineation challenging on T1WI. In this study, we aimed to introduce and validate a method that incorporates quantitative susceptibility mapping (QSM) into the rs-fMRI analytical pipeline to achieve precise subcortical nuclei segmentation and improve the stability of RSFC measurements in Parkinson's disease. A total of 321 participants (148 patients with Parkinson's Disease and 173 normal controls) were enrolled. We performed cross-modal registration at the individual level for rs-fMRI to QSM (FUNC2QSM) and T1WI (FUNC2T1), respectively.The consistency and accuracy of resting state functional connectivity (RSFC) measurements in two registration approaches were assessed by intraclass correlation coefficient and mutual information. Bootstrap analysis was performed to validate the stability of the RSFC differences between Parkinson's disease and normal controls. RSFC-based machine learning models were constructed for Parkinson's disease classification, using optimized hyperparameters (RandomizedSearchCV with 5-fold cross-validation). The consistency of RSFC measurements between the two registration methods was poor, whereas the QSM-guided approach showed better mutual information values, suggesting higher registration accuracy. The disruptions of RSFC identified with the QSM-guided approach were more stable and reliable, as confirmed by bootstrap analysis. In classification models, the QSM-guided method consistently outperformed the T1WI-guided method, achieving higher test-set ROC-AUC values (FUNC2QSM: 0.87-0.90, FUNC2T1: 0.67-0.70). The QSM-guided approach effectively enhanced the accuracy of subcortical segmentation and the stability of RSFC measurement, thus facilitating future biomarker development in Parkinson's disease.

Details DOI

ICML Conference 2025 Conference Paper

Robust Multi-bit Text Watermark with LLM-based Paraphrasers

Xiaojun Xu
Jinghan Jia
Yuanshun Yao
Yang Liu
Hang Li 0001

We propose an imperceptible multi-bit text watermark embedded by paraphrasing with LLMs. We fine-tune a pair of LLM paraphrasers that are designed to behave differently so that their paraphrasing difference reflected in the text semantics can be identified by a trained decoder. To embed our multi-bit watermark, we use two paraphrasers alternatively to encode the pre-defined binary code at the sentence level. Then we use a text classifier as the decoder to decode each bit of the watermark. Through extensive experiments, we show that our watermarks can achieve over 99. 99% detection AUC with small (1. 1B) text paraphrasers while keeping the semantic information of the original sentence. More importantly, our pipeline is robust under word substitution and sentence paraphrasing perturbations and generalizes well to out-of-distributional data. We also show the stealthiness of our watermark with LLM-based evaluation.

Details

JBHI Journal 2024 Journal Article

Brain Age Prediction Based on Quantitative Susceptibility Mapping Using the Segmentation Transformer

Mingxing Chen
Yiqing Wang
Yuting Shi
Jie Feng
Ruimin Feng
Xiaojun Guan
Xiaojun Xu
Yuyao Zhang

The process of brain aging is intricate, encompassing significant structural and functional changes, including myelination and iron deposition in the brain. Brain age could act as a quantitative marker to evaluate the degree of the individual's brain evolution. Quantitative susceptibility mapping (QSM) is sensitive to variations in magnetically responsive substances such as iron and myelin, making it a favorable tool for estimating brain age. In this study, we introduce an innovative 3D convolutional network named Segmentation-Transformer-Age-Network (STAN) to predict brain age based on QSM data. STAN employs a two-stage network architecture. The first-stage network learns to extract informative features from the QSM data through segmentation training, while the second-stage network predicts brain age by integrating the global and local features. We collected QSM images from 712 healthy participants, with 548 for training and 164 for testing. The results demonstrate that the proposed method achieved a high accuracy brain age prediction with a mean absolute error (MAE) of 4. 124 years and a coefficient of determination (R 2 ) of 0. 933. Furthermore, the gaps between the predicted brain age and the chronological age of Parkinson's disease patients were significantly higher than those of healthy subjects (P<0. 01). We thus believe that using QSM-based predicted brain age offers a more reliable and accurate phenotype, with the potentiality to serve as a biomarker to explore the process of advanced brain aging.

Details DOI

ICLR Conference 2024 Conference Paper

Effective and Efficient Federated Tree Learning on Hybrid Data

Qinbin Li
Chulin Xie
Xiaojun Xu
Xiaoyuan Liu
Ce Zhang 0001
Bo Li 0026
Bingsheng He
Dawn Song

Federated learning has emerged as a promising distributed learning paradigm that facilitates collaborative learning among multiple parties without transferring raw data. However, most existing federated learning studies focus on either horizontal or vertical data settings, where the data of different parties are assumed to be from the same feature or sample space. In practice, a common scenario is the hybrid data setting, where data from different parties may differ both in the features and samples. To address this, we propose HybridTree, a novel federated learning approach that enables federated tree learning on hybrid data. We observe the existence of consistent split rules in trees. With the help of these split rules, we theoretically show that the knowledge of parties can be incorporated into the lower layers of a tree. Based on our theoretical analysis, we propose a layer-level solution that does not need frequent communication traffic to train a tree. Our experiments demonstrate that HybridTree can achieve comparable accuracy to the centralized setting with low computational and communication overhead. HybridTree can achieve up to 8 times speedup compared with the other baselines.

Details

NeurIPS Conference 2024 Conference Paper

Large Language Model Unlearning

Yuanshun Yao
Xiaojun Xu

We study how to perform unlearning, i. e. forgetting undesirable (mis)behaviors, on large language models (LLMs). We show at least three scenarios of aligning LLMs with human preferences can benefit from unlearning: (1) removing harmful responses, (2) erasing copyright-protected content as requested, and (3) reducing hallucinations. Unlearning, as an alignment technique, has three advantages. (1) It only requires negative (e. g. harmful) examples, which are much easier and cheaper to collect (e. g. via red teaming or user reporting) than positive (e. g. helpful and often human-written) examples required in the standard alignment process. (2) It is computationally efficient. (3) It is especially effective when we know which training samples cause the misbehavior. To the best of our knowledge, our work is among the first to explore LLM unlearning. We are also among the first to formulate the settings, goals, and evaluations in LLM unlearning. Despite only having negative samples, our ablation study shows that unlearning can still achieve better alignment performance than RLHF with just 2% of its computational time.

PDF Details DOI

YNIMG Journal 2023 Journal Article

Predictability of inter-regional cerebral perfusion similarity on dopamine responsiveness and the moderation role of cognition in PD patients

Zhengye Cao
Chenqing Wu
Hui Hong
Peiyu Huang
Cheng Zhou
Xiaojun Guan
Haoting Wu
Xiaojie Duanmu

BACKGROUND: Large heterogeneity can be found in dopamine responsiveness of patients with Parkinson's disease (PD). Instantly and objectively understanding dopamine responsiveness of patients may help clinical practice. PURPOSE: This PD study explored the predictability of off-state inter-regional cerebral blood flow (CBF) perfusion similarity on patient's dopamine responsiveness and tested whether the predictive power could be moderated by patient's cognitive status. MATERIALS AND METHOD: The PD cohort with 192 patients (containing off state and on state (PD-off and PD-on)) and the normal control (NC) cohort with 92 subjects were included. The intra-individual CBF relative variation networks were constructed and compared between PD-off and PD-on, PD-off and NC to identify the alterations caused by dopamine depletion. Based on that, regression analysis of off-state inter-regional CBF perfusion similarity on patient's dopamine responsiveness was performed. Finally, moderation analysis was conducted to test the moderation role of cognition on the regression model. RESULTS: In the PD-off cohort, a total of 82 edges in the network were identified that affected by dopamine depletion. Off-state inter-regional CBF perfusion similarity was found that had a significant influence on patient's dopamine responsiveness. Cognitive status was validated that positively moderated the relationship between off-state inter-regional CBF perfusion similarity and dopamine responsiveness. CONCLUSION: Dopamine responsiveness of PD patient could be predicted by off-state inter-regional CBF perfusion similarity. Patient's cognitive status might have a positive moderation effect on his/her dopamine responsiveness.

Details DOI

ICML Conference 2022 Conference Paper

Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization

Xiaojun Xu
Jacky Y. Zhang
Evelyn Ma
Hyun Ho Son
Sanmi Koyejo
Bo Li 0026

Machine learning (ML) robustness and domain generalization are fundamentally correlated: they essentially concern data distribution shifts under adversarial and natural settings, respectively. On one hand, recent studies show that more robust (adversarially trained) models are more generalizable. On the other hand, there is a lack of theoretical understanding of their fundamental connections. In this paper, we explore the relationship between regularization and domain transferability considering different factors such as norm regularization and data augmentations (DA). We propose a general theoretical framework proving that factors involving the model function class regularization are sufficient conditions for relative domain transferability. Our analysis implies that “robustness" is neither necessary nor sufficient for transferability; rather, regularization is a more fundamental perspective for understanding domain transferability. We then discuss popular DA protocols (including adversarial training) and show when they can be viewed as the function class regularization under certain conditions and therefore improve generalization. We conduct extensive experiments to verify our theoretical findings and show several counterexamples where robustness and generalization are negatively correlated on different datasets.

Details

YNIMG Journal 2022 Journal Article

Altered brain iron depositions from aging to Parkinson's disease and Alzheimer's disease: A quantitative susceptibility mapping study

Xiaojun Guan
Tao Guo
Cheng Zhou
Jingjing Wu
Qingze Zeng
Kaicheng Li
Xiao Luo
Xueqin Bai

Brain iron deposition is a promising marker for human brain health, providing insightful information for understanding aging as well as neurodegenerations, e. g. , Parkinson's disease (PD) and Alzheimer's disease (AD). To comprehensively evaluate brain iron deposition along with aging, PD-related neurodegeneration, from prodromal PD (pPD) to clinical PD (cPD), and AD-related neurodegeneration, from mild cognitive impairment (MCI) to AD, a total of 726 participants from July 2013 to December 2020, including 100 young adults, 189 old adults, 184 pPD, 171 cPD, 31 MCI and 51 AD patients, were included. Quantitative susceptibility mapping data were acquired and used to quantify regional magnetic susceptibility, and the resulting spatial standard deviations were recorded. A general linear model was applied to perform the inter-group comparison. As a result, relative to young adults, old adults showed significantly higher iron deposition with higher spatial variation in all of the subcortical nuclei (p < 0. 01). pPD showed a high spatial variation of iron distribution in the subcortical nuclei except for substantia nigra (SN); and iron deposition in SN and red nucleus (RN) were progressively increased from pPD to cPD (p < 0. 01). AD showed significantly higher iron deposition in caudate and putamen with higher spatial variation compared with old adults, pPD and cPD (p < 0. 01), and significant iron deposition in SN compared with old adults (p < 0. 01). Also, linear regression models had significances in predicting motor score in pPD and cPD (Rmean = 0. 443, Ppermutation = 0. 001) and cognition score in MCI and AD (Rmean = 0. 243, Ppermutation = 0. 037). In conclusion, progressive iron deposition in the SN and RN may characterize PD-related neurodegeneration, namely aging to cPD through pPD. On the other hand, extreme iron deposition in the caudate and putamen may characterize AD-related neurodegeneration.

Details DOI

NeurIPS Conference 2022 Conference Paper

LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness

Xiaojun Xu
Linyi Li
Bo Li

Recent studies show that training deep neural networks (DNNs) with Lipschitz constraints are able to enhance adversarial robustness and other model properties such as stability. In this paper, we propose a layer-wise orthogonal training method (LOT) to effectively train 1-Lipschitz convolution layers via parametrizing an orthogonal matrix with an unconstrained matrix. We then efficiently compute the inverse square root of a convolution kernel by transforming the input domain to the Fourier frequency domain. On the other hand, as existing works show that semi-supervised training helps improve empirical robustness, we aim to bridge the gap and prove that semi-supervised learning also improves the certified robustness of Lipschitz-bounded models. We conduct comprehensive evaluations for LOT under different settings. We show that LOT significantly outperforms baselines regarding deterministic l2 certified robustness, and scales to deeper neural networks. Under the supervised scenario, we improve the state-of-the-art certified robustness for all architectures (e. g. from 59. 04% to 63. 50% on CIFAR-10 and from 32. 57% to 34. 59% on CIFAR-100 at radius $\rho=36/255$ for 40-layer networks). With semi-supervised learning over unlabelled data, we are able to improve state-of-the-art certified robustness on CIFAR-10 at $\rho=108/255$ from 36. 04% to 42. 39%. In addition, LOT consistently outperforms baselines on different model architectures with only 1/3 evaluation time.

PDF Details

ICLR Conference 2022 Conference Paper

On the Certified Robustness for Ensemble Models and Beyond

Zhuolin Yang
Linyi Li 0001
Xiaojun Xu
Bhavya Kailkhura
Tao Xie 0001
Bo Li 0026

Recent studies show that deep neural networks (DNN) are vulnerable to adversarial examples, which aim to mislead DNNs by adding perturbations with small magnitude. To defend against such attacks, both empirical and theoretical defense approaches have been extensively studied for a single ML model. In this work, we aim to analyze and provide the certified robustness for ensemble ML models, together with the sufficient and necessary conditions of robustness for different ensemble protocols. Although ensemble models are shown more robust than a single model empirically; surprisingly, we find that in terms of the certified robustness the standard ensemble models only achieve marginal improvement compared to a single model. Thus, to explore the conditions that guarantee to provide certifiably robust ensemble ML models, we first prove that diversified gradient and large confidence margin are sufficient and necessary conditions for certifiably robust ensemble models under the model-smoothness assumption. We then provide the bounded model-smoothness analysis based on the proposed Ensemble-before-Smoothing strategy. We also prove that an ensemble model can always achieve higher certified robustness than a single base model under mild conditions. Inspired by the theoretical findings, we propose the lightweight Diversity Regularized Training (DRT) to train certifiably robust ensemble ML models. Extensive experiments show that our DRT enhanced ensembles can consistently achieve higher certified robustness than existing single and ensemble ML models, demonstrating the state-of-the-art certified $L_2$-robustness on MNIST, CIFAR-10, and ImageNet datasets.

Details

YNICL Journal 2021 Journal Article

Locus coeruleus degeneration is associated with disorganized functional topology in Parkinson’s disease

Cheng Zhou
Tao Guo
Xueqin Bai
Jingjing Wu
Ting Gao
Xiaojun Guan
Xiaocao Liu
Luyan Gu

Degeneration of the locus coeruleus (LC) is recognized as a critical hallmark of Parkinson's disease (PD). Recent studies have reported that noradrenaline produced from the LC has critical effects on brain functional organization. However, it is unknown if LC degeneration in PD contributes to cognitive/motor manifestations through modulating brain functional organization. This study enrolled 94 PD patients and 68 healthy controls, and LC integrity was measured using the contrast-to-noise ratio of the LC (CNRLC) calculated from T1-weighted magnetic resonance imaging. We used graph-theory-based network analysis to characterize brain functional organization. The relationships among LC degeneration, network disruption, and cognitive/motor manifestations in PD were assessed. Whether network disruption was a mediator between LC degeneration and cognitive/motor impairments was assessed further. In addition, an independent PD subgroup (n = 35) having functional magnetic resonance scanning before and after levodopa administration was enrolled to evaluate whether LC degeneration-related network deficiencies were independent of dopamine deficiency. We demonstrated that PD patients have significant LC degeneration compared to healthy controls. CNRLC was positively correlated with Montreal Cognitive Assessment score and the nodal efficiency (NE) of several cognitive-related regions. Lower NE of the superior temporal gyrus was a mediator between LC degeneration and cognitive impairment in PD. However, levodopa treatment could not normalize the reduced NE of the superior temporal gyrus (mediator). In conclusion, we provided evidence for the relationship between LC degeneration and extensive network disruption in PD, and highlight the role of network disorganization in LC degeneration-related cognitive impairment.

Details DOI

NeurIPS Conference 2021 Conference Paper

TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness

Zhuolin Yang
Linyi Li
Xiaojun Xu
Shiliang Zuo
Qian Chen
Pan Zhou
Benjamin Rubinstein
Ce Zhang

Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better protect ML systems against adversarial attacks, several questions are raised: what are the sufficient conditions for adversarial transferability, and how to bound it? Is there a way to reduce the adversarial transferability in order to improve the robustness of an ensemble ML model? To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness. Our theoretical analysis shows that only promoting the orthogonality between gradients of base models is not enough to ensure low transferability; in the meantime, the model smoothness is an important factor to control the transferability. We also provide the lower and upper bounds of adversarial transferability under certain conditions. Inspired by our theoretical analysis, we propose an effective Transferability Reduced Smooth (TRS) ensemble training strategy to train a robust ensemble with low transferability by enforcing both gradient orthogonality and model smoothness between base models. We conduct extensive experiments on TRS and compare with 6 state-of-the-art ensemble baselines against 8 whitebox attacks on different datasets, demonstrating that the proposed TRS outperforms all baselines significantly.

PDF Details

YNICL Journal 2019 Journal Article

Gray matter structural covariance networks changes along the Alzheimer's disease continuum

Kaicheng Li
Xiao Luo
Qingze Zeng
Peiyu Huang
Zhujing Shen
Xiaojun Xu
Jingjing Xu
Chao Wang

Alzheimer's disease (AD) has a long neuropathological accumulation phase before the onset of dementia. Such AD neuropathological deposition between neurons impairs the synaptic communication, resulting in networks disorganization. Our study aimed to explore the evolution patterns of gray matter structural covariance networks (SCNs) along AD continuum. Based on the AT(N) (i. e. , Amyloid/Tau/Neurodegeneration) pathological classification system, we classified subjects into four groups using cerebrospinal fluid amyloid-beta1–42 (A) and phosphorylated tau protein181 (T). We identified 101 subjects with normal AD biomarkers (A-T-), 40 subjects with Alzheimer's pathologic change (A + T−), 101 subjects with biological AD (A + T+) and 91 AD with dementia (demented subjects with A + T+). We used four regions of interest to anchor default mode network (DMN, medial temporal subsystem and midline core subsystem), salience network (SN) and executive control network (ECN). Finally, we used a multi-regression model-based linear-interaction analysis to assess the SCN changes. Along the disease progression, DMN and SN showed increased structural association at the early stage while decreased structural association at the late stage. Moreover, ECN showed progressively increased structural association as AD neuropathological profiles progress. In conclusion, this study found the dynamic trajectory of SCNs changes along the AD continuum and support the network disconnection hypothesis underlying AD neuropathological progression. Further, SCN may potentially serve as an effective AD biomarker.

Details DOI

AAAI Conference 2018 Conference Paper

A Neural Stochastic Volatility Model

Rui Luo
Weinan Zhang
Xiaojun Xu
Jun Wang

In this paper, we show that the recent integration of statistical models with deep recurrent neural networks provides a new way of formulating volatility (the degree of variation of time series) models that have been widely used in time series analysis and prediction in ﬁnance. The model comprises a pair of complementary stochastic recurrent neural networks: the generative network models the joint distribution of the stochastic volatility process; the inference network approximates the conditional distribution of the latent variables given the observables. Our focus here is on the formulation of temporal dynamics of volatility over time under a stochastic recurrent neural network framework. Experiments on real-world stock price datasets demonstrate that the proposed model generates a better volatility estimation and prediction that outperforms mainstream methods, e. g. , deterministic models such as GARCH and its variants, and stochastic models namely the MCMC-based stochvol as well as the Gaussian-processbased, on average negative log-likelihood.

PDF Details

YNIMG Journal 2008 Journal Article

Age, gender, and hemispheric differences in iron deposition in the human brain: An in vivo MRI study

Xiaojun Xu
Qidong Wang
Minming Zhang

It is well known that iron accumulates in the brains of patients with various neurodegenerative diseases. To better understand disease-related iron changes, it is necessary to know the physiological distribution and accumulation of iron in the human brain. Studies have shown that brain iron levels increase with aging. However, the effects of gender and hemispheric laterality on iron accumulation and distribution are not well established. In this study, we estimated the brain iron levels in vivo in 78 healthy adults ranging in age 22 to 78 years using magnetic susceptibility-weighted phase imaging. The effects of age, gender, and hemispheric location on brain iron levels were evaluated within the framework of a general linear model. We found that the left hemisphere had higher iron levels than the right in the putamen, globus pallidus, substantia nigra, thalamus, and frontal white matter. We argue that the hemispheric asymmetry of iron content may underlie that of the dopaminergic system and may be related to motor lateralization in humans. In addition, significant age-related iron accumulation occurred in the putamen, red nucleus, and frontal white matter, but no gender-related differences in iron levels were detected. The results of this study extend our knowledge of the physiological distribution and accumulation of iron in the human brain.

Details DOI