Jiayu Zhou

Jiayu Zhou

Auto-generated profile, based on publicly available information

Jiayu Zhou

School of Information, University of Michigan, USA

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 July 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
Zhuangdi ZhuZhuangdi Zhu
Zhuangdi Zhu
KLKaixiang Lin
Kaixiang Lin
AJAnil K. Jain
Anil K. Jain
JZJiayu Zhou
Jiayu Zhou
Reinforcement learning is a learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in reinforcement learning upon the fast development of deep neural networks. Along with the promising prospects of reinforcement learning in numerous domains such as robotics and game-playing, transfer learning has arisen to tackle various challenges faced by reinforcement learning, by transferring knowledge from external expertise to facilitate the efficiency and effectiveness of the learning process. In this survey, we systematically investigate the recent progress of transfer learning approaches in the context of deep reinforcement learning. Specifically, we provide a framework for categorizing the state-of-the-art transfer learning approaches, under which we analyze their goals, methodologies, compatible reinforcement learning backbones, and practical applications. We also draw connections between transfer learning and other relevant topics from the reinforcement learning perspective and explore their potential challenges that await future research progress.

22 June 2024 in ACM Computing Surveys
Verified
Journal Article
Open access
JWJiajun Wu
Jiajun Wu
FDFan Dong
Fan Dong
Henry LeungHenry Leung
Henry Leung
Zhuangdi ZhuZhuangdi Zhu
Zhuangdi Zhu
JZJiayu Zhou
Jiayu Zhou
SDSteve Drew
Steve Drew
The ultra-low latency requirements of 5G/6G applications and privacy constraints call for distributed machine learning systems to be deployed at the edge. With its simple yet effective approach, federated learning (FL) is a natural solution for massive user-owned devices in edge computing with distributed and private training data. FL methods based on FedAvg typically follow a naive star topology, ignoring the heterogeneity and hierarchy of the volatile edge computing architectures and topologies in reality. Several other network topologies exist and can address the limitations and bottlenecks of the star topology. This motivates us to survey network topology-related FL solutions. In this paper, we conduct a comprehensive survey of the existing FL works focusing on network topologies. After a brief overview of FL and edge computing networks, we discuss various edge network topologies as well as their advantages and disadvantages. Lastly, we discuss the remaining challenges and future works for applying FL to topology-specific edge networks.

8 December 2022 in ACM Transactions on Sensor Networks
Verified
Journal Article
Open access
XOXiaomin Ouyang
Xiaomin Ouyang
ZXZhiyuan Xie
Zhiyuan Xie
JZJiayu Zhou
Jiayu Zhou
GXGuoliang Xing
Guoliang Xing
JHJianwei Huang
Jianwei Huang
Federated Learning (FL) has recently received significant interest, thanks to its capability of protecting data privacy. However, existing FL paradigms yield unsatisfactory performance for a wide class of human activity recognition (HAR) applications, since they are oblivious to the intrinsic relationship between data of different users. We propose ClusterFL, a clustering-based federated learning system that can provide high model accuracy and low communication overhead for HAR applications. ClusterFL features a novel clustered multi-task federated learning framework that minimizes the empirical training loss of multiple learned models while automatically capturing the intrinsic clustering relationship among the nodes. We theoretically prove the convergence of proposed FL framework for non-convex and strongly convex models and provide the guidance on selection of hyper-parameters for achieving such convergence. Based on the learned cluster relationship, ClusterFL can efficiently drop the nodes that converge slower or have little correlations with others in each cluster, significantly speeding up the convergence while maintaining the accuracy performance. We evaluate the performance of ClusterFL on an NVIDIA edge testbed using four new HAR datasets collected from 145 users. The results show that ClusterFL outperforms several state-of-the-art FL paradigms in terms of overall accuracy and can save more than 50% communication overhead.

6 January 2022 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
ZLZhizhe Liu
Zhizhe Liu
ZZZhenfeng Zhu
Zhenfeng Zhu
SZShuai Zheng
Shuai Zheng
YLYang Liu
Yang Liu
JZJiayu Zhou
Jiayu Zhou
YZYao Zhao
Yao Zhao
To bridge the gap between the source and target domains in unsupervised domain adaptation (UDA), the most common strategy puts focus on matching the marginal distributions in the feature space through adversarial learning. However, such category-agnostic global alignment lacks of exploiting the class-level joint distributions, causing the aligned distribution less discriminative. To address this issue, we propose in this paper a novel margin preserving self-paced contrastive Learning (MPSCL) model for cross-modal medical image segmentation. Unlike the conventional construction of contrastive pairs in contrastive learning, the domain-adaptive category prototypes are utilized to constitute the positive and negative sample pairs. With the guidance of progressively refined semantic prototypes, a novel margin preserving contrastive loss is proposed to boost the discriminability of embedded representation space. To enhance the supervision for contrastive learning, more informative pseudo-labels are generated in target domain in a self-paced way, thus benefiting the category-aware distribution alignment for UDA. Furthermore, the domain-invariant representations are learned through joint contrastive learning between the two domains. Extensive experiments on cross-modal cardiac segmentation tasks demonstrate that MPSCL significantly improves semantic segmentation performance, and outperforms a wide variety of state-of-the-art methods by a large margin.

18 June 2023
Verified
Conference Paper
Open access
XOXiaomin Ouyang
Xiaomin Ouyang
ZXZhiyuan Xie
Zhiyuan Xie
HFHeming Fu
Heming Fu
SCSitong Cheng
Sitong Cheng
LPLi Pan
Li Pan
JHJianwei Huang
Jianwei Huang

4 June 2018 in JAMIA Open
Verified
Journal Article
Open access
PDF file
FTFengyi Tang
Fengyi Tang
CXCao Xiao
Cao Xiao
FWFei Wang
Fei Wang
JZJiayu Zhou
Jiayu Zhou
Objective: The growing availability of rich clinical data such as patients’ electronic health records provide great opportunities to address a broad range of real-world questions in medicine. At the same time, artificial intelligence and machine learning (ML)-based approaches have shown great premise on extracting insights from those data and helping with various clinical problems. The goal of this study is to conduct a systematic comparative study of different ML algorithms for several predictive modeling problems in urgent care. Design: We assess the performance of 4 benchmark prediction tasks (eg mortality and prediction, differential diagnostics, and disease marker discovery) using medical histories, physiological time-series, and demographics data from the Medical Information Mart for Intensive Care (MIMIC-III) database. Measurements: For each given task, performance was estimated using standard measures including the area under the receiver operating characteristic (AUC) curve, F-1 score, sensitivity, and specificity. Microaveraged AUC was used for multiclass classification models. Results and Discussion: Our results suggest that recurrent neural networks show the most promise in mortality prediction where temporal patterns in physiologic features alone can capture in-hospital mortality risk (AUC > 0.90). Temporal models did not provide additional benefit compared to deep models in differential diagnostics. When comparing the training–testing behaviors of readmission and mortality models, we illustrate that readmission risk may be independent of patient stability at discharge. We also introduce a multiclass prediction scheme for length of stay which preserves sensitivity and AUC with outliers of increasing duration despite decrease in sample size.