Author name cluster

Yuan Chen

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.

8 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling

Hong Huang
Jinhai Yang
Yuan Chen
Jiaxun Ye
Dapeng Wu

Federated Learning (FL) enables collaborative model training across distributed clients without data sharing, but its high computational and communication demands strain resource-constrained devices. While existing methods use dynamic pruning to improve efficiency by periodically adjusting sparse model topologies while maintaining sparsity, these approaches suffer from issues such as greedy adjustments, unstable topologies, and communication inefficiency, resulting in less robust models and suboptimal performance under data heterogeneity and partial client availability. To address these challenges, we propose Fed erated R obust pruning via combinatorial T hompson S ampling (FedRTS), a novel framework designed to develop robust sparse models. FedRTS enhances robustness and performance through its Thompson Sampling-based Adjustment (TSAdj) mechanism, which uses probabilistic decisions informed by stable and farsighted information, instead of deterministic decisions reliant on unstable and myopic information in previous methods. Extensive experiments demonstrate that FedRTS achieves state-of-the-art performance in computer vision and natural language processing tasks while reducing communication costs, particularly excelling in scenarios with heterogeneous data distributions and partial client participation. Our codes are available at: https: //github. com/Little0o0/FedRTS.

PDF Details

AAAI Conference 2024 Conference Paper

Stereo Vision Conversion from Planar Videos Based on Temporal Multiplane Images

Shanding Diao
Yuan Chen
Yang Zhao
Wei Jia
Zhao Zhang
Ronggang Wang

With the rapid development of 3D movie and light-field displays, there is a growing demand for stereo videos. However, generating high-quality stereo videos from planar videos remains a challenging task. Traditional depth-image-based rendering techniques struggle to effectively handle the problem of occlusion exposure, which occurs when the occluded contents become visible in other views. Recently, the single-view multiplane images (MPI) representation has shown promising performance for planar video stereoscopy. However, the MPI still lacks real details that are occluded in the current frame, resulting in blurry artifacts in occlusion exposure regions. In fact, planar videos can leverage complementary information from adjacent frames to predict a more complete scene representation for the current frame. Therefore, this paper extends the MPI from still frames to the temporal domain, introducing the temporal MPI (TMPI). By extracting complementary information from adjacent frames based on optical flow guidance, obscured regions in the current frame can be effectively repaired. Additionally, a new module called masked optical flow warping (MOFW) is introduced to improve the propagation of pixels along optical flow trajectories. Experimental results demonstrate that the proposed method can generate high-quality stereoscopic or light-field videos from a single view and reproduce better occluded details than other state-of-the-art (SOTA) methods. https://github.com/Dio3ding/TMPI

PDF Details DOI

EAAI Journal 2023 Journal Article

An exploitation-boosted sine cosine algorithm for global optimization

Changlun Li
Ke Liang
Yuan Chen
Mingzhang Pan

The sine cosine algorithm (SCA) has drawn significant attention from researchers in different fields because of fewer control parameters, excellent global optimization ability, and simple principles. However, there are some drawbacks of the SCA which needed immediate attention. The position-updated equation of the SCA is good at exploration but poor at exploitation, which leads to slow converging speed and low converging accuracy in some complex cases. Therefore, an exploitation-boosted sine cosine algorithm (namely, EBSCA) is proposed in this study. In order to enhance the ability of exploitation, a new position-updated equation is designed by emphasizing the position information of the best individual, thereby guiding the updating of new candidate individuals. Meanwhile, the information weights of the best individual and the current individual in the new equation are dynamically adjusted by a balance factor b to avoid over-exploitation of the information from the best individual. Furthermore, a new integration way of combining the quantization orthogonal crossover strategy with the SCA is proposed to improve the utilizing efficiency of the searching space. The performance of the EBSCA is evaluated by being tested on 13 classical benchmark functions, IEEE CEC 2015 problems, and four well-known engineering applications. The comparisons demonstrate that the EBSCA algorithm obviously improves the performance of the SCA. Additionally, the experimental results show that, the proposed EBSCA algorithm exhibits higher competitiveness compared to other algorithms participated in this research.

Details DOI

IROS Conference 2023 Conference Paper

Automated Key Action Detection for Closed Reduction of Pelvic Fractures by Expert Surgeons in Robot-Assisted Surgery

Mingzhang Pan
Ya-Wen Deng
Zhen Li 0049
Yuan Chen
Xiao-Lan Liao
Gui-Bin Bian

Pelvic fractures are one of the most serious traumas in orthopedics, and the technical proficiency and expertise of the surgical team strongly influence the quality of reduction results. With the advancement of information technology and robotics, robot-assisted pelvic fracture reduction surgery is expected to reduce the impact caused by inexperienced doctors and improve the accuracy and stability of pelvic reduction. However, this requires the robot to detect key surgeon actions from time-series data, enabling the robot to independently perceive the surgical status, predict the surgeon's intentions, assess the demonstrated level of professional competence, and assess the progress of the surgery. Therefore, a multi-task deep learning neural network architecture is proposed, which incorporates Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) along with tri-modality fusion and feature extraction techniques. The proposed framework aims to achieve key action detection in closed reduction operations for pelvic fractures. Subsequently, a trimodal fine-grained dataset was constructed, wherein 29, 32, and 14 labels were marked on flexion, position, and pressure data for 14 key closed reduction actions. The experimental results show that the correct detection rate of closed reduction actions is 92. 3 %, significantly higher than the commonly used recognition algorithms. This work provides a method for the robot to learn the surgeon's professional knowledge, provides the basis for the operation's motion perception, and contributes to the autonomy of the robot-assisted closed reduction surgery of pelvic fractures.

Details

YNICL Journal 2023 Journal Article

Resting-state functional connectivity of the raphe nuclei in major depressive Disorder: A Multi-site study

Yajuan Zhang
Chu-Chung Huang
Jiajia Zhao
Yuchen Liu
Mingrui Xia
Xiaoqin Wang
Dongtao Wei
Yuan Chen

Accumulating evidence showed that major depressive disorder (MDD) is characterized by a dysfunction of serotonin neurotransmission. Raphe nuclei are the sources of most serotonergic neurons that project throughout the brain. Incorporating measurements of activity within the raphe nuclei into the analysis of connectivity characteristics may contribute to understanding how neurotransmitter synthesized centers are involved in thepathogenesisof MDD. Here, we analyzed the resting-state functional magnetic resonance imaging (RS-fMRI) dataset from 1,148 MDD patients and 1,079 healthy individuals recruited across nine centers. A seed-based analysis with the dorsal raphe and median raphe nuclei was performed to explore the functional connectivity (FC) alterations. Compared to controls, for dorsal raphe, the significantly decreased FC linking with the right precuneus and median cingulate cortex were found; for median raphe, the increased FC linking with right superior cerebellum (lobules V/VI) was found in MDD patients. In further exploratory analyzes, MDD-related connectivity alterations in dorsal and median raphe nuclei in different clinical factors remained highly similar to the main findings, indicating these abnormal connectivities are a disease-related alteration. Our study highlights a functional dysconnection pattern of raphe nuclei in MDD with multi-site big data. These findings help improve our understanding of the pathophysiology of depression and provide evidence of the theoretical foundation for the development of novel pharmacotherapies.

Details DOI

NeurIPS Conference 2021 Conference Paper

Dynamic COVID risk assessment accounting for community virus exposure from a spatial-temporal transmission model

Yuan Chen
Wenbo Fei
Qinxia Wang
Donglin Zeng
Yuanjia Wang

COVID-19 pandemic has caused unprecedented negative impacts on our society, including further exposing inequity and disparity in public health. To study the impact of socioeconomic factors on COVID transmission, we first propose a spatial-temporal model to examine the socioeconomic heterogeneity and spatial correlation of COVID-19 transmission at the community level. Second, to assess the individual risk of severe COVID-19 outcomes after a positive diagnosis, we propose a dynamic, varying-coefficient model that integrates individual-level risk factors from electronic health records (EHRs) with community-level risk factors. The underlying neighborhood prevalence of infections (both symptomatic and pre-symptomatic) predicted from the previous spatial-temporal model is included in the individual risk assessment so as to better capture the background risk of virus exposure for each individual. We design a weighting scheme to mitigate multiple selection biases inherited in EHRs of COVID patients. We analyze COVID transmission data in New York City (NYC, the epicenter of the first surge in the United States) and EHRs from NYC hospitals, where time-varying effects of community risk factors and significant interactions between individual- and community-level risk factors are detected. By examining the socioeconomic disparity of infection risks and interaction among the risk factors, our methods can assist public health decision-making and facilitate better clinical management of COVID patients.

PDF Details

NeurIPS Conference 2020 Conference Paper

Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment

Yuan Chen
Donglin Zeng
Tianchen Xu
Yuanjia Wang

For mental disorders, patients' underlying mental states are non-observed latent constructs which have to be inferred from observed multi-domain measurements such as diagnostic symptoms and patient functioning scores. Additionally, substantial heterogeneity in the disease diagnosis between patients needs to be addressed for optimizing individualized treatment policy in order to achieve precision medicine. To address these challenges, we propose an integrated learning framework that can simultaneously learn patients' underlying mental states and recommend optimal treatments for each individual. This learning framework is based on the measurement theory in psychiatry for modeling multiple disease diagnostic measures as arising from the underlying causes (true mental states). It allows incorporation of the multivariate pre- and post-treatment outcomes as well as biological measures while preserving the invariant structure for representing patients' latent mental states. A multi-layer neural network is used to allow complex treatment effect heterogeneity. Optimal treatment policy can be inferred for future patients by comparing their potential mental states under different treatments given the observed multi-domain pre-treatment measurements. Experiments on simulated data and a real-world clinical trial data show that the learned treatment polices compare favorably to alternative methods on heterogeneous treatment effects, and have broad utilities which lead to better patient outcomes on multiple domains.

PDF Details

EAAI Journal 2016 Journal Article

Image denoising by using PDE and GCV in tetrolet transform domain

Changjiang Zhang
Yuan Chen
Chunjiang Duanmu
Yinhuan Yang

The proposed algorithm, which uses partial differential equations (PDE) and generalized cross validation (GCV) theory in the tetrolet transform domain, is used to reduce the noise in an image. Tetrolet transform is applied to decompose the noisy image and GCV theory is used to determine the optimal denoising threshold in the tetrolet transform domain. Then inverse tetrolet transform is used to the modified tetrolet transform coefficients to obtain initial denoising image. PDE model is employed to reduce the block effect which is occurred by only using tetrolet transform to reduce noise, and keeping the edge information. The proposed image denoising algorithm is compared with five similar image denoising algorithms: wavelet transform combined with PDE, contourlet transform combined with PDE, curvelet transform combined PDE, shearlet transform combined with PDE and tetrolet transform combined with PDE, respectively. The experimental results show that comprehensive denoising performance of the proposed algorithm combined with PM1 model (Tetrolet+GCV+PM1) is optimal, especially when PSNR is low. More edges and details can be remained well by the proposed algorithm.

Details DOI