arXiv subjects

Jian Kang

Publications and source records attributed to Jian Kang.

At least 127 records · Page 7Linked to original sources

arXiv2022

M2HF: Multi-level Multi-modal Hybrid Fusion for Text-Video Retrieval

Videos contain multi-modal content, and exploring multi-level cross-modal interactions with natural language queries can provide great prominence to text-video retrieval task (TVR). However, new trending methods applying large-scale pre-trained model CLIP for TVR do not focus on multi-modal cues in videos. Furthermore, the traditional methods simply concatenating multi-modal features do not exploit fine-grained cross-modal information in videos. In this paper, we propose a multi-level multi-modal hybrid fusion (M2HF) network to explore comprehensive interactions between text queries and each modality content in videos. Specifically, M2HF first utilizes visual features extracted by CLIP to early fuse with audio and motion features extracted from videos, obtaining audio-visual fusion features and motion-visual fusion features respectively. Multi-modal alignment problem is also considered in this process. Then, visual features, audio-visual fusion features, motion-visual fusion features, and texts extracted from videos establish cross-modal relationships with caption queries in a multi-level way. Finally, the retrieval outputs from all levels are late fused to obtain final text-video retrieval results. Our framework provides two kinds of training strategies, including an ensemble manner and an end-to-end manner. Moreover, a novel multi-modal balance loss function is proposed to balance the contributions of each modality for efficient end-to-end training. M2HF allows us to obtain state-of-the-art results on various benchmarks, eg, Rank@1 of 64.9\%, 68.2\%, 33.2\%, 57.1\%, 57.8\% on MSR-VTT, MSVD, LSMDC, DiDeMo, and ActivityNet, respectively.

cs.MM↗

arXiv2022

Deep Historical Borrowing Framework to Prospectively and Simultaneously Synthesize Control Information in Confirmatory Clinical Trials with Multiple Endpoints

In current clinical trial development, historical information is receiving more attention as it provides utility beyond sample size calculation. Meta-analytic-predictive (MAP) priors and robust MAP priors have been proposed for prospectively borrowing historical data on a single endpoint. To simultaneously synthesize control information from multiple endpoints in confirmatory clinical trials, we propose to approximate posterior probabilities from a Bayesian hierarchical model and estimate critical values by deep learning to construct pre-specified strategies for hypothesis testing. This feature is important to ensure study integrity by establishing prospective decision functions before the trial conduct. Simulations are performed to show that our method properly controls family-wise error rate (FWER) and preserves power as compared with a typical practice of choosing constant critical values given a subset of null space. Satisfactory performance under prior-data conflict is also demonstrated. We further illustrate our method using a case study in Immunology.

stat.ME↗

arXiv2022

Finite-Sample Two-Group Composite Hypothesis Testing via Machine Learning

In the problem of composite hypothesis testing, identifying the potential uniformly most powerful (UMP) unbiased test is of great interest. Beyond typical hypothesis settings with exponential family, it is usually challenging to prove the existence and further construct such UMP unbiased tests with finite sample size. For example in the COVID-19 pandemic with limited previous assumptions on the treatment for investigation and the standard of care, adaptive clinical trials are appealing due to ethical considerations, and the ability to accommodate uncertainty while conducting the trial. Although several methods have been proposed to control type I error rates, how to find a more powerful hypothesis testing strategy is still an open question. Motivated by this problem, we propose an automatic framework of constructing test statistics and corresponding critical values via machine learning methods to enhance power in a finite sample. In this article, we particularly illustrate the performance using Deep Neural Networks (DNN) and discuss its advantages. Simulations and two case studies of adaptive designs demonstrate that our method is automatic, general and pre-specified to construct statistics with satisfactory power in finite-sample. Supplemental materials are available online including R code and an R shiny app.

stat.ME↗

arXiv2022

Optimizing Graphical Procedures for Multiplicity Control in a Confirmatory Clinical Trial via Deep Learning

In confirmatory clinical trials, it has been proposed to use a simple iterative graphical approach to construct and perform intersection hypotheses tests with a weighted Bonferroni-type procedure to control type I errors in the strong sense. Given Phase II study results or other prior knowledge, it is usually of main interest to find the optimal graph that maximizes a certain objective function in a future Phase III study. In this article, we evaluate the performance of two existing derivative-free constrained methods, and further propose a deep learning enhanced optimization framework. Our method numerically approximates the objective function via feedforward neural networks (FNNs) and then performs optimization with available gradient information. It can be constrained so that some features of the testing procedure are held fixed while optimizing over other features. Simulation studies show that our FNN-based approach has a better balance between robustness and time efficiency than some existing derivative-free constrained optimization algorithms. Compared to the traditional stochastic search method, our optimizer has moderate multiplicity adjusted power gain when the number of hypotheses is relatively large. We further apply it to a case study to illustrate how to optimize a multiple testing procedure with respect to a specific study objective.

stat.ME↗

arXiv2022

Composite Scores for Transplant Center Evaluation: A New Individualized Empirical Null Method

Risk-adjusted quality measures are used to evaluate healthcare providers while controlling for factors beyond their control. Existing healthcare provider profiling approaches typically assume that the risk adjustment is perfect and the between-provider variation in quality measures is entirely due to the quality of care. However, in practice, even with very good models for risk adjustment, some between-provider variation will be due to incomplete risk adjustment, which should be recognized in assessing and monitoring providers. Otherwise, conventional methods disproportionately identify larger providers as outliers, even though their provider effects need not be "extreme.'' Motivated by efforts to evaluate the quality of care provided by transplant centers, we develop a composite evaluation score based on a novel individualized empirical null method, which robustly accounts for overdispersion due to unobserved risk factors, models the marginal variance of standardized scores as a function of the effective center size, and only requires the use of publicly-available center-level statistics. The evaluations of United States kidney transplant centers based on the proposed composite score are substantially different from those based on conventional methods. Simulations show that the proposed empirical null approach more accurately classifies centers in terms of quality of care, compared to existing methods.

stat.AP↗

arXiv2022

Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition

General accent recognition (AR) models tend to directly extract low-level information from spectrums, which always significantly overfit on speakers or channels. Considering accent can be regarded as a series of shifts relative to native pronunciation, distinguishing accents will be an easier task with accent shift as input. But due to the lack of native utterance as an anchor, estimating the accent shift is difficult. In this paper, we propose linguistic-acoustic similarity based accent shift (LASAS) for AR tasks. For an accent speech utterance, after mapping the corresponding text vector to multiple accent-associated spaces as anchors, its accent shift could be estimated by the similarities between the acoustic embedding and those anchors. Then, we concatenate the accent shift with a dimension-reduced text vector to obtain a linguistic-acoustic bimodal representation. Compared with pure acoustic embedding, the bimodal representation is richer and more clear by taking full advantage of both linguistic and acoustic information, which can effectively improve AR performance. Experiments on Accented English Speech Recognition Challenge (AESRC) dataset show that our method achieves 77.42% accuracy on Test set, obtaining a 6.94% relative improvement over a competitive system in the challenge.

cs.SD↗

arXiv2022

Density Regression and Uncertainty Quantification with Bayesian Deep Noise Neural Networks

Deep neural network (DNN) models have achieved state-of-the-art predictive accuracy in a wide range of supervised learning applications. However, accurately quantifying the uncertainty in DNN predictions remains a challenging task. For continuous outcome variables, an even more difficult problem is to estimate the predictive density function, which not only provides a natural quantification of the predictive uncertainty, but also fully captures the random variation in the outcome. In this work, we propose the Bayesian Deep Noise Neural Network (B-DeepNoise), which generalizes standard Bayesian DNNs by extending the random noise variable from the output layer to all hidden layers. The latent random noise equips B-DeepNoise with the flexibility to approximate highly complex predictive distributions and accurately quantify predictive uncertainty. For posterior computation, the unique structure of B-DeepNoise leads to a closed-form Gibbs sampling algorithm that iteratively simulates from the posterior full conditional distributions of the model parameters, circumventing computationally intensive Metropolis-Hastings methods. A theoretical analysis of B-DeepNoise establishes a recursive representation of the predictive distribution and decomposes the predictive variance with respect to the latent parameters. We evaluate B-DeepNoise against existing methods on benchmark regression datasets, demonstrating its superior performance in terms of prediction accuracy, uncertainty quantification accuracy, and uncertainty quantification efficiency. To illustrate our method's usefulness in scientific studies, we apply B-DeepNoise to predict general intelligence from neuroimaging features in the Adolescent Brain Cognitive Development (ABCD) project.

cs.LG↗

arXiv2022

A Soft-Thresholding Operator for Sparse Time-Varying Effects in Survival Models

We consider a class of Cox models with time-dependent effects that may be zero over certain unknown time regions or, in short, sparse time-varying effects. The model is particularly useful for biomedical studies as it conveniently depicts the gradual evolution of effects of risk factors on survival. Statistically, estimating and drawing inference on infinite dimensional functional parameters with sparsity (e.g., time-varying effects with zero-effect time intervals) present enormous challenges. To address them, we propose a new soft-thresholding operator for modeling sparse, piecewise smooth and continuous time-varying coefficients in a Cox time-varying effects model. Unlike the common regularized methods, our approach enables one to estimate non-zero time-varying effects and detect zero regions simultaneously, and construct a new type of sparse confidence intervals that accommodate zero regions. This leads to a more interpretable model with a straightforward inference procedure. We develop an efficient algorithm for inference in the target functional space, show that the proposed method enjoys desired theoretical properties, and present its finite sample performance by way of simulations. We apply the proposed method to analyze the data of the Boston Lung Cancer Survivor Cohort, an epidemiological cohort study investigating the impacts of risk factors on lung cancer survival, and obtain clinically useful results.

stat.ME↗

arXiv2022

Adversarial Sample Detection for Speaker Verification by Neural Vocoders

Automatic speaker verification (ASV), one of the most important technology for biometric identification, has been widely adopted in security-critical applications. However, ASV is seriously vulnerable to recently emerged adversarial attacks, yet effective countermeasures against them are limited. In this paper, we adopt neural vocoders to spot adversarial samples for ASV. We use the neural vocoder to re-synthesize audio and find that the difference between the ASV scores for the original and re-synthesized audio is a good indicator for discrimination between genuine and adversarial samples. This effort is, to the best of our knowledge, among the first to pursue such a technical direction for detecting time-domain adversarial samples for ASV, and hence there is a lack of established baselines for comparison. Consequently, we implement the Griffin-Lim algorithm as the detection baseline. The proposed approach achieves effective detection performance that outperforms the baselines in all the settings. We also show that the neural vocoder adopted in the detection framework is dataset-independent. Our codes will be made open-source for future works to do fair comparison.

cs.SD↗

arXiv2022

Individualized Risk Assessment of Preoperative Opioid Use by Interpretable Neural Network Regression

Preoperative opioid use has been reported to be associated with higher preoperative opioid demand, worse postoperative outcomes, and increased postoperative healthcare utilization and expenditures. Understanding the risk of preoperative opioid use helps establish patient-centered pain management. In the field of machine learning, deep neural network (DNN) has emerged as a powerful means for risk assessment because of its superb prediction power; however, the blackbox algorithms may make the results less interpretable than statistical models. Bridging the gap between the statistical and machine learning fields, we propose a novel Interpretable Neural Network Regression (INNER), which combines the strengths of statistical and DNN models. We use the proposed INNER to conduct individualized risk assessment of preoperative opioid use. Intensive simulations and an analysis of 34,186 patients expecting surgery in the Analgesic Outcomes Study (AOS) show that the proposed INNER not only can accurately predict the preoperative opioid use using preoperative characteristics as DNN, but also can estimate the patient specific odds of opioid use without pain and the odds ratio of opioid use for a unit increase in the reported overall body pain, leading to more straightforward interpretations of the tendency to use opioids than DNN. Our results identify the patient characteristics that are strongly associated with opioid use and is largely consistent with the previous findings, providing evidence that INNER is a useful tool for individualized risk assessment of preoperative opioid use.

cs.LG↗

arXiv2022

Leveraging Phone Mask Training for Phonetic-Reduction-Robust E2E Uyghur Speech Recognition

In Uyghur speech, consonant and vowel reduction are often encountered, especially in spontaneous speech with high speech rate, which will cause a degradation of speech recognition performance. To solve this problem, we propose an effective phone mask training method for Conformer-based Uyghur end-to-end (E2E) speech recognition. The idea is to randomly mask off a certain percentage features of phones during model training, which simulates the above verbal phenomena and facilitates E2E model to learn more contextual information. According to experiments, the above issues can be greatly alleviated. In addition, deep investigations are carried out into different units in masking, which shows the effectiveness of our proposed masking unit. We also further study the masking method and optimize filling strategy of phone mask. Finally, compared with Conformer-based E2E baseline without mask training, our model demonstrates about 5.51% relative Word Error Rate (WER) reduction on reading speech and 12.92% on spontaneous speech, respectively. The above approach has also been verified on test-set of open-source data THUYG-20, which shows 20% relative improvements.

cs.SD↗

arXiv2022

Image Response Regression via Deep Neural Networks

Delineating the associations between images and a vector of covariates is of central interest in medical imaging studies. To tackle this problem of image response regression, we propose a novel nonparametric approach in the framework of spatially varying coefficient models, where the spatially varying functions are estimated through deep neural networks. Compared to existing solutions, the proposed method explicitly accounts for spatial smoothness and subject heterogeneity, has straightforward interpretations, and is highly flexible and accurate in capturing complex association patterns. A key idea in our approach is to treat the image voxels as the effective samples, which not only alleviates the limited sample size issue that haunts the majority of medical imaging studies, but also leads to more robust and reproducible results. Focusing on a broad family of piecewise smooth functions, we establish the estimation and selection consistency, and derive the asymptotic error bounds. We demonstrate the efficacy of the method through intensive simulations, and further illustrate its advantages with analyses of two functional magnetic resonance imaging datasets.

stat.ML↗

arXiv2022

RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network

Graph Convolutional Network (GCN) plays pivotal roles in many real-world applications. Despite the successes of GCN deployment, GCN often exhibits performance disparity with respect to node degrees, resulting in worse predictive accuracy for low-degree nodes. We formulate the problem of mitigating the degree-related performance disparity in GCN from the perspective of the Rawlsian difference principle, which is originated from the theory of distributive justice. Mathematically, we aim to balance the utility between low-degree nodes and high-degree nodes while minimizing the task-specific loss. Specifically, we reveal the root cause of this degree-related unfairness by analyzing the gradients of weight matrices in GCN. Guided by the gradients of weight matrices, we further propose a pre-processing method RawlsGCN-Graph and an in-processing method RawlsGCN-Grad that achieves fair predictive accuracy in low-degree nodes without modification on the GCN architecture or introduction of additional parameters. Extensive experiments on real-world graphs demonstrate the effectiveness of our proposed RawlsGCN methods in significantly reducing degree-related bias while retaining comparable overall performance.

cs.LG↗

arXiv2022

Bayesian learning of COVID-19 Vaccine safety while incorporating Adverse Events ontology

While vaccines are crucial to end the COVID-19 pandemic, public confidence in vaccine safety has always been vulnerable. Many statistical methods have been applied to VAERS (Vaccine Adverse Event Reporting System) database to study the safety of COVID-19 vaccines. However, all these methods ignored the adverse event (AE) ontology. AEs are naturally related; for example, events of retching, dysphagia, and reflux are all related to an abnormal digestive system. Explicitly bringing AE relationships into the model can aid in the detection of true AE signals amid the noise while reducing false positives. We propose a Bayesian graphical model to estimate all AEs while incorporating the AE ontology simultaneously. We proposed strategies to construct conjugate forms leading to an efficient Gibbs sampler. Built upon the posterior distributions, we proposed a negative control approach to mitigate reporting bias and an enrichment approach to detect AE groups of concern. The proposed methods were evaluated using simulation studies and were further illustrated on studying the safety of COVID-19 vaccines. The proposed methods were implemented in R package \textit{BGrass} and source code are available at https://github.com/BangyaoZhao/BGrass.

stat.ME↗

arXiv2021

Robust High-Dimensional Regression with Coefficient Thresholding and its Application to Imaging Data Analysis

It is of importance to develop statistical techniques to analyze high-dimensional data in the presence of both complex dependence and possible outliers in real-world applications such as imaging data analyses. We propose a new robust high-dimensional regression with coefficient thresholding, in which an efficient nonconvex estimation procedure is proposed through a thresholding function and the robust Huber loss. The proposed regularization method accounts for complex dependence structures in predictors and is robust against outliers in outcomes. Theoretically, we analyze rigorously the landscape of the population and empirical risk functions for the proposed method. The fine landscape enables us to establish both {statistical consistency and computational convergence} under the high-dimensional setting. The finite-sample properties of the proposed method are examined by extensive simulation studies. An illustration of real-world application concerns a scalar-on-image regression analysis for an association of psychiatric disorder measured by the general factor of psychopathology with features extracted from the task functional magnetic resonance imaging data in the Adolescent Brain Cognitive Development study.

stat.ME↗

arXiv2021

Realization of Topological Mott Insulator in a Twisted Bilayer Graphene Lattice Model

Magic-angle twisted bilayer graphene has recently become a thriving material platform realizing correlated electron phenomena taking place within its topological flat bands. Several numerical and analytical methods have been applied to understand the correlated phases therein, revealing some similarity with the quantum Hall physics. In this work, we provide a Mott-Hubbard perspective for the TBG system. Employing the large-scale density matrix renormalization group on the lattice model containing the projected Coulomb interactions only, we identify a first-order quantum phase transition between the insulating stripe phase and the quantum anomalous Hall state with the Chern number of $\pm 1$. Our results not only shed light on the mechanism of the quantum anomalous Hall state discovered at three-quarters filling, but also provide an example of the topological Mott insulator, i.e., the quantum anomalous Hall state in the strong coupling limit.

cond-mat.str-el↗

arXiv2021

BigEarthNet Dataset with A New Class-Nomenclature for Remote Sensing Image Understanding

This paper presents BigEarthNet that is a large-scale Sentinel-2 multispectral image dataset with a new class nomenclature to advance deep learning (DL) studies in remote sensing (RS). BigEarthNet is made up of 590,326 image patches annotated with multi-labels provided by the CORINE Land Cover (CLC) map of 2018 based on its most thematic detailed Level-3 class nomenclature. Initial research demonstrates that some CLC classes are challenging to be accurately described by considering only Sentinel-2 images. To increase the effectiveness of BigEarthNet, in this paper we introduce an alternative class-nomenclature to allow DL models for better learning and describing the complex spatial and spectral information content of the Sentinel-2 images. This is achieved by interpreting and arranging the CLC Level-3 nomenclature based on the properties of Sentinel-2 images in a new nomenclature of 19 classes. Then, the new class-nomenclature of BigEarthNet is used within state-of-the-art DL models in the context of multi-label classification. Results show that the models trained from scratch on BigEarthNet outperform those pre-trained on ImageNet, especially in relation to some complex classes including agriculture, other vegetated and natural environments. All DL models are made publicly available at http://bigearth.net/#downloads, offering an important resource to guide future progress on RS image analysis.

cs.CV↗

arXiv2021

Momentum space quantum Monte Carlo on twisted bilayer Graphene

We report an implementation of the momentum space quantum Monte Carlo (QMC) method on the interaction model for the twisted bilayer graphene (TBG) at integer fillings. The long-range Coulomb repulsion is treated exactly with the flat bands, spin and valley degrees of freedom of electrons taking into account. We prove the absence of the minus sign problem for QMC simulation at integer fillings when either the two valley or the two spin degrees of freedom are considered. By taking the realistic parameters of the twist angle and interlayer tunnelings into the simulation, we benchmark the QMC data with the exact band gap obtained at the chiral limit, to reveal the insulating ground states at the charge neutrality point (CNP). Then, with the exact Green's functions from QMC, we perform stochastic analytic continuation to obtain the first set of single-particle spectral function for the TBG model at CNP. Our momentum space QMC scheme therefore offers the controlled computation pathway for systematic investigation of the electronic states in realistic TBG model at various electron fillings.

cond-mat.str-el↗