GYGuosheng Yin

Guosheng Yin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Guosheng Yin has a total of 244 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Bayesian knockoff filter for controlling false discovery rate

    by Jiaqi Gu, Guosheng Yin, Jun S. Liu

    In many scientific fields, researchers are interested in discovering features with substantial effects on the response from a large number of candidate features while controlling the proportion of false discoveries. By incorporating the knockoff procedure in a Bayesian framework, we develop the Bayesian knockoff filter (BKF) for selecting important features. The BKF is built upon a tight upper bound for the posterior probability of the null hypothesis, which is derived under the Bayesian “flip-sign” property implied by our procedure. In contrast to the standard knockoff methods in the frequentist paradigm, we allow the knockoff variables to be generated in every iteration of the Markov chain Monte Carlo procedure, which removes the unwanted variability of the single-knockoff generation (knockoff is typically generated only once before the model fitting). Compared with multi-knockoffs, the BKF is more principled and natural in incorporating side information through prior distributions under a fully Bayesian framework. We further develop an e-value BKF approach to theoretically guarantee the frequentist false discovery rate (FDR) control. Numerical experiments on both synthetic and real data demonstrate the advantages of the BKF over existing knockoff methods and Bayesian variable selection approaches, i.e., the BKF possesses comparable power, yields a lower FDR and more stable selection sets.

  • Open Access

    Nonparametric inference for censored data using deep neural networks

    by Wen Su, Qiang Wu, Kin-Yat Liu, Guosheng Yin, Jian Huang, Xingqiu Zhao

    We propose a novel deep learning approach to nonparametric statistical inference for the conditional hazard function of survival time with right-censored data. We use a deep neural network (DNN) to approximate the logarithm of a conditional hazard function given covariates and obtain a DNN likelihood-based estimator of the conditional hazard function. Such an estimation approach enhances model flexibility and hence relaxes structural and functional assumptions on conditional hazard or survival functions. We establish the nonasymptotic error bound and functional asymptotic normality of the proposed estimator. Subsequently, we develop new one-sample tests for goodness-of-fit evaluation and two-sample tests for treatment comparison. Notably, we design a new test specifically tailored for testing nonparametric Cox models. The consistency of these tests is established by analyzing the power functions. Both simulation studies and real application analysis show superior performances of the proposed estimators and tests in comparison with existing methods.

  • Open Access

    Patient Retreat in Dose Escalation for Phase I Clinical Trials With Rare Diseases

    by Jialu Fang, Guosheng Yin

    Phase I clinical trials aim to identify the maximum tolerated dose (MTD), a task that becomes challenging in rare disease due to limited patient recruitment. Traditional dose‐finding designs, which assign one dose per patient, require a sufficient sample size that may be infeasible for rare disease trials. To address these limitations, we propose the patient retreat in dose escalation (PRIDE) scheme, which integrates intra‐patient dose escalation and considers intra‐patient correlations by incorporating random effects into a Bayesian hierarchical framework. We further introduce PRIDE‐FA (flexible allocation), an extension of PRIDE with a flexible allocation strategy. By allowing retreated patients to be assigned to any dose level based on trial needs, PRIDE‐FA improves resource efficiency, leading to greater reductions in required sample size and trial duration. This paper incorporates random effects into established dose‐finding designs, including the calibration‐free odds (CFO) design, the Bayesian optimal interval (BOIN) design, and the continual reassessment method (CRM) to account for intra‐patient correlations when each patient may receive multiple doses. Simulation studies demonstrate that PRIDE and PRIDE‐FA significantly improve the accuracy of MTD selection, reduce required sample size, and shorten trial duration compared to existing dose‐finding methods. Together, PRIDE and PRIDE‐FA provide a robust and efficient framework for phase I clinical trials with rare diseases.

  • SIB-MIL: Sparsity-Induced Bayesian Neural Network for Robust Multiple Instance Learning on Whole Slide Image Analysis

    by Yihang Chen, Tsai Hor Chan, Jianning Chen, Li Liang, Guosheng Yin, Lequan Yu

    Multiple instance learning (MIL) has shown prominent success in analyzing whole slide histopathology images (WSIs). However, existing MIL methods often suffer from overfitting due to weak supervision and the “needle-in-a-haystack” nature of WSIs. Additionally, most deterministic approaches lack a mechanism for uncertainty quantification. While Bayesian neural networks (BNNs) have emerged as a promising solution to mitigate overfitting and enable uncertainty estimation by imposing prior constraints, commonly used Gaussian BNNs exhibit unstable posterior predictive distributions under weak supervision and suffer from high prediction variance. To tackle these challenges, we propose a sparsity-induced Bayesian Neural Network to be adopted in the MIL scheme, named SIB-MIL, for robust WSI prediction. Instead of using Gaussian prior distributions, we place a sparsity-induced prior, the Horse-shoe prior, on the BNN parameters to address the variance overflowing issue. Such sparsity also filters unimportant noise and highlights salient regions, which only occupy a small proportion in WSIs. Empirical evaluations on cancer classification and subtyping tasks corroborate that not only can our method improve the existing MIL networks, but it also performs well in uncertainty quantification. Codes are available at https://github.com/HKU-MedAI/SIB-MIL.


  • Decision Tables for Calibration-Free Odds Design in Phase I Clinical Trials

    by Ninghao Zhang, Guosheng Yin

    In clinical trials, the initial step typically involves assessing a new drug's toxicity profile, aiming to identify a tolerable dose level for subsequent studies. In phase I trials, the primary objective is to determine the maximum tolerated dose, defined as the highest dose associated with an acceptable level of toxicity. Numerous methods have been developed to guide dose escalation and de-escalation decisions during trial conduct. Among these approaches, the calibration-free odds (CFO) design has demonstrated superior operating characteristics and has emerged as one of the most effective approaches for dose finding. To facilitate the application of the CFO design in clinical trial practice, an R package and a Shiny app have been released. This study presents CFO decision tables in Excel files to further remove the barrier of applying the CFO design to real trials. Anyone involved in the trial conduct can implement the CFO design with no difficulties. During the trial, dose movement decisions can be made simply by referring to the cumulative data (including numbers of patients treated and observed toxicities) and the pregenerated decision tables, without any additional statistical calculation. This approach significantly enhances the usability of the CFO design and reduces the operational complexity associated with its implementation in clinical trials. The Excel CFO decision tables can be downloaded from CFO Shiny App.

  • Open Access

    Variational Polya Tree

    by Lu Xu, Tsai Hor Chan, Kwok Fai Lam, Lequan Yu, Guosheng Yin

    Density estimation is essential for generative modeling, particularly with the rise of modern neural networks. While existing methods capture complex data distributions, they often lack interpretability and uncertainty quantification. Bayesian nonparametric methods, especially the \polya tree, offer a robust framework that addresses these issues by accurately capturing function behavior over small intervals. Traditional techniques like Markov chain Monte Carlo (MCMC) face high computational complexity and scalability limitations, hindering the use of Bayesian nonparametric methods in deep learning. To tackle this, we introduce the variational \polya tree (VPT) model, which employs stochastic variational inference to compute posterior distributions. This model provides a flexible, nonparametric Bayesian prior that captures latent densities and works well with stochastic gradient optimization. We also leverage the joint distribution likelihood for a more precise variational posterior approximation than traditional mean-field methods. We evaluate the model performance on both real data and images, and demonstrate its competitiveness with other state-of-the-art deep density estimation methods. We also explore its ability in enhancing interpretability and uncertainty quantification. Code is available at https://github.com/howardchanth/var-polya-tree.

  • Open Access

    Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process

    by Tsai Hor Chan, Feng Wu, Yihang Chen, Guosheng Yin, Lequan Yu

    Developing effective multimodal fusion approaches has become increasingly essential in many real-world scenarios, such as health care and finance. The key challenge is how to preserve the feature expressiveness in each modality while learning cross-modal interactions. Previous approaches primarily focus on the cross-modal alignment, while over-emphasis on the alignment of marginal distributions of modalities may impose excess regularization and obstruct meaningful representations within each modality. The Dirichlet process (DP) mixture model is a powerful Bayesian non-parametric method that can amplify the most prominent features by its richer-gets-richer property, which allocates increasing weights to them. Inspired by this unique characteristic of DP, we propose a new DP-driven multimodal learning framework that automatically achieves an optimal balance between prominent intra-modal representation learning and cross-modal alignment. Specifically, we assume that each modality follows a mixture of multivariate Gaussian distributions and further adopt DP to calculate the mixture weights for all the components. This paradigm allows DP to dynamically allocate the contributions of features and select the most prominent ones, leveraging its richer-gets-richer property, thus facilitating multimodal feature fusion. Extensive experiments on several multimodal datasets demonstrate the superior performance of our model over other competitors. Ablation analysis further validates the effectiveness of DP in aligning modality distributions and its robustness to changes in key hyperparameters. Code is anonymously available at https://github.com/HKU-MedAI/DPMM.git

  • Open Access

    Ensemble Manifold Learning via Model Averaging

    by Ruoxu Tan, Guosheng Yin

    Manifold learning aims to extract information of high-dimensional data and provide low-dimensional representations while preserving nonlinear structures of the input data. Numerous manifold learning algorithms have been proposed in the literature. We develop a model averaging procedure to combine different manifold learning algorithms for enhancing the robustness of the result. Toward this goal, we propose a new quality metric that is tuning-free and scale-invariant by utilizing the Mahalanobis distance. The quality metric can also be used for selection of tuning parameters. By optimizing the weights and ensembling different approaches, our model averaging manifold learning method is shown to achieve more robust results, because no single method in the ensemble can dominate others in all scenarios. Through synthetic and real data examples, we show that the new metric outperforms existing ones and the model averaging outcome provides a unanimously superior outcome that is always competitive with respect to visualization or classification under different contexts.

  • Open Access

    Effective Sample Size Estimation Based on the Concordance Between p-Value and Posterior Probability of the Null Hypothesis

    by Han Wang, Yan Dora Zhang, Guosheng Yin

    Estimating the effective sample size (ESS) of a prior distribution is an age-old yet pivotal challenge, with great implications for clinical trials and various biomedical applications. Although numerous endeavors have been dedicated to this pursuit, most of them neglect the likelihood context in which the prior is embedded, thereby considering all priors as “beneficial”. In the limited studies of addressing harmful priors, specifying a baseline prior remains an indispensable step. By means of the elegant bridge between the p-value and the posterior probability of the null hypothesis, we propose a new ESS estimation method based on p-value in the framework of hypothesis testing, expanding the scope of existing ESS estimation methods in three key aspects: (i) We address the specific likelihood context of the prior, enabling the possibility of negative ESS values in case of prior–likelihood disconcordance; (ii) By leveraging the well-established bridge between the frequentist and Bayesian configurations under noninformative priors, there is no need to specify a baseline prior which incurs another criticism of subjectivity; (iii) By incorporating ESS into the hypothesis testing framework, our hypothesis test-based ESS estimation method transcends the conventional one-ESS-one-prior paradigm and accommodates one-ESS-multiple-priors paradigm, where the sole ESS may reflect the collaborative impact of multiple priors in diverse contexts. Through comprehensive simulation analyses, we demonstrate the superior performance of the hypothesis test-based ESS estimation method in comparison with existing approaches. Furthermore, by applying this approach to an expression quantitative trait loci (eQTL) data analysis, we show the effectiveness of informative priors in uncovering gene eQTL loci.

    • 9 October 2025
    • Published by HAL in HAL
    Open Access

    One-sample survival tests in the presence of non-proportional hazards in oncology clinical trial

    by Szurewsky Chloé, Guosheng Yin, Gwénaël Le Teuff

    In oncology, conduct well-powered time-to-event randomized clinical trials may be challenging due to limited patients number. Many designs for single-arm trials (SATs) have recently emerged as an alternative to overcome this issue. They rely on the (modified) one-sample log-rank test (OSLRT) under the proportional hazards to compare the survival curves of an experimental and an external control group. We extend Finkelstein's formulation of OSLRT as a score test by using a piecewise exponential model for early, middle and delayed treatment effects and an accelerated hazards model for crossing hazards. We adapt the restricted mean survival time based test and construct a combination test procedure (max-Combo) to SATs. The performance of the developed tests are evaluated through a simulation study. The score tests are as conservative as the OSLRT and have the highest power when the data generation matches the model underlying score tests. The max-Combo test is more powerful than the OSLRT whatever the scenarios and is thus an interesting approach as compared to a score test. Uncertainty on the survival curve estimate of the external control group and its model misspecification may have a significant impact on performance. For illustration, we apply the developed tests on real data examples.