Yawei Zhao

Yawei Zhao

Auto-generated profile, based on publicly available information

Yawei Zhao

Medical Big Data Research Center, Chinese PLA General Hospital

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
22 April 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
MLMeng Liu
Meng Liu
KLKe Liang
Ke Liang
YZYawei Zhao
Yawei Zhao
WTWenxuan Tu
Wenxuan Tu
SZSihang Zhou
Sihang Zhou
KHKunlun He
Kunlun He
Temporal graph learning aims to generate high-quality representations for graph-based tasks with dynamic information, which has recently garnered increasing attention. In contrast to static graphs, temporal graphs are typically organized as node interaction sequences over continuous time rather than an adjacency matrix. Most temporal graph learning methods model current interactions by incorporating historical neighborhood. However, such methods only consider first-order temporal information while disregarding crucial high-order structural information, resulting in suboptimal performance. To address this issue, we propose a self-supervised method called S2T for temporal graph learning, which extracts both temporal and structural information to learn more informative node representations. Notably, the initial node representations combine first-order temporal and high-order structural information differently to calculate two conditional intensities. An alignment loss is then introduced to optimize the node representations, narrowing the gap between the two intensities and making them more informative. Concretely, in addition to modeling temporal information using historical neighbor sequences, we further consider structural knowledge at both local and global levels. At the local level, we generate structural intensity by aggregating features from high-order neighbor sequences. At the global level, a global representation is generated based on all nodes to adjust the structural intensity according to the active statuses on different nodes. Extensive experiments demonstrate that the proposed model S2T achieves at most 10.13% performance improvement compared with the state-of-the-art competitors on several datasets.

7 December 2022 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
PCPeipei Chen
Peipei Chen
XLXueshan Luo
Xueshan Luo
DGDeke Guo
Deke Guo
YSYuchen Sun
Yuchen Sun
JXJunjie Xie
Junjie Xie
RZRui Zhou
Rui Zhou
The promise of unmanned aerial vehicles (UAVs) combined with the mobile edge computing (MEC), named MECaided-UAV extends the MEC application to offer new flexible, low-latency computing services and considerable utilities for pervasive sensing of the world. In MEC, the UAV with limited onboard energy and computation resources needs to offload its tasks to resource-rich ground base stations (GBSs) servers. Because of the broadcast nature of line-of-sight (LoS) channels, one of the key challenges in task offloading is to guarantee that confidential data is offloaded safely to the GBSs without being intercepted by eavesdroppers (Eves). In this MEC-aided-UAV system, the GBSs help the UAV compute the offloaded tasks and transmit the artificial noise (AN) to suppress the vicious Eves.We make the first attempt to study the maximum-minimum average secrecy capacity problem, including joint optimization of the trajectory and transmit power of the UAV, the transmit power of AN, the local computation ratio, and the selection of GBSs with consideration of the practical constraints of completion delay of the tasks, maximum velocity, and the power consumption. The optimization issue is confirmed as a mixed-integer nonconvex problem. Thereafter, a low-complexity iterative algorithm with the block coordinate descent method and successive convex approximation technique is put forward to get its suboptimal solution. In addition, the convergent solution can be achieved by solving the subproblems in turn. Evaluation results validate that the proposed secure offloading scheme significantly effectiveness the baselines by 17.4%-71.2% on the maximum-minimum average secrecy capacity

13 December 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
ZLZhizhe Liu
Zhizhe Liu
ZZZhenfeng Zhu
Zhenfeng Zhu
SZShuai Zheng
Shuai Zheng
YZYawei Zhao
Yawei Zhao
KHKunlun He
Kunlun He
YZYao Zhao
Yao Zhao
Automated radiology report generation aims to generate accurate and radiologist-like descriptions for the patient's images, which can greatly relieve the workload of radiologists. However, due to the data bias and long report problems, medical report generation has been a challenging task. In this paper, we propose a Flexible Multi-view Paradigm (FMVP) for medical report generation in a novel observation-to-concept manner. It first makes some medical observations automatically or with the help of a radiologist on the patient's image to obtain patientrelated priori knowledge, just as radiologists do in practice. Furthermore, to bridge the gap between pretrain and generation phases, the hierarchical alignment is proposed to jointly conduct the implicit alignment between region-tag and the explicit global alignment of the image-report pair. Finally, a compatible decoder towards decoding the fused multi-view knowledge is proposed to capture more complementary information for the report generation, which breaks the traditional entrenched decoding mechanism guided by visual information. Extensive quantitative and qualitative experiments on the public MIMIC-CXR and IU-Xray datasets show that our model achieves competitive performance compared to state-of-the-art methods.

13 August 2018 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YZYawei Zhao
Yawei Zhao
Kai XuKai Xu
Kai Xu
EZEn Zhu
En Zhu
XLXinwang Liu
Xinwang Liu
XZXinzhong Zhu
Xinzhong Zhu
JYJianping Yin
Jianping Yin
Recently, network lasso has drawn many attentions due to its remarkable performance on simultaneous clustering and optimization. However, it usually suffers from the imperfect data (noise, missing values etc), and yields sub-optimal solutions. The reason is that it finds the similar instances according to their features directly, which is usually impacted by the imperfect data, and thus returns sub-optimal results. In this paper, we propose triangle lasso to avoid its disadvantage. Triangle lasso finds the similar instances according to their neighbours. If two instances have many common neighbours, they tend to become similar. Although some instances are profiled by the imperfect data, it is still able to find the similar counterparts. Furthermore, we develop an efficient algorithm based on Alternating Direction Method of Multipliers (ADMM) to obtain a moderately accurate solution. In addition, we present a dual method to obtain the accurate solution with the low additional time consumption. We demonstrate through extensive numerical experiments that triangle lasso is robust to the imperfect data. It usually yields a better performance than the state-of-the-art method when performing data analysis tasks in practical scenarios.

1 January 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZLZhizhe Liu
Zhizhe Liu
SZShuai Zheng
Shuai Zheng
XSXiaoyi Sun
Xiaoyi Sun
ZZZhenfeng Zhu
Zhenfeng Zhu
YZYawei Zhao
Yawei Zhao
YZYao Zhao
Yao Zhao
Due to the various appearance of the polyps and the tiny contrast between the polyp area and its surrounding background, accurate polyp segmentation has become a challenging task. To tackle this issue, we introduce a boundary-enhanced framework for polyp segmentation, called the Focused on Boundary Segmentation (FoBS) framework, that leverages multi-level collaboration among sample, feature, and optimization. It places greater emphasis on the polyp boundary to improve the accuracy of segmentation. Firstly, a boundary-aware mixup method is designed to improve the model’s awareness of the boundary. More importantly, we propose deformable laplacian-based feature refining to explicitly strengthen the representation ability of the boundary features. It employs a deformable Laplacian refinement function to capture discriminative information from a deformable perceptual field, thereby improving its ability to adapt to boundary variations. In addition, we introduce the self-adjusting refinement coefficient learning that enables adaptive control over the refinement strength at each location. Furthermore, we develop a location-sensitive compensation criterion that assigns more importance to the degraded feature after feature refinement during optimization. Extensive quantitative and qualitative experiments on four polyp benchmarks demonstrate the effectiveness of our method for automatic polyp segmentation. Our code is available at https://github.com/TFboys-lzz/ FoBS.

22 June 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
YZYawei Zhao
Yawei Zhao
SQShuang Qiu
Shuang Qiu
KLKuan Li
Kuan Li
LLLailong Luo
Lailong Luo
JYJianping Yin
Jianping Yin
JLJi Liu
Ji Liu
In online learning, the dynamic regret metric chooses the reference oracle that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The dynamic regret metric is particularly interesting for applications, such as online recommendation (since the customers' preference always evolves over time). While the online gradient (OG) method has been shown to be optimal for the static regret metric, the optimal algorithm for the dynamic regret remains unknown. In this article, we show that proximal OG (a general version of OG) is optimum to the dynamic regret by showing that the proved lower bound matches the upper bound. It is highlighted that we provide a new and general lower bound of dynamic regret. It provides new understanding about the difficulty to follow the dynamics in the online setting.