Yi Zhu

Yi Zhu

Auto-generated profile, based on publicly available information

Yi Zhu

School of Information Technology, Jiangsu Open University, Nanjing 210036, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
13 December 2024 in Pattern Recognition
Verified
Journal Article
Closed access
QZQian Zhang
Qian Zhang
YZYi Zhu
Yi Zhu
FCFilipe Rolim Cordeiro
Filipe Rolim Cordeiro
QCQiu Chen
Qiu Chen

29 March 2024 in Expert Systems with Applications
Verified
Journal Article
Open access
QZQian Zhang
Qian Zhang
YZYi Zhu
Yi Zhu
MYMing Yang
Ming Yang
GJGe Jin
Ge Jin
YZYingWen Zhu
YingWen Zhu
QCQiu Chen
Qiu Chen

10 July 2024 in Entropy
Verified
Journal Article
Open access
PDF file
QZQian Zhang
Qian Zhang
GJGe Jin
Ge Jin
YZYi Zhu
Yi Zhu
HWHongjian Wei
Hongjian Wei
QCQiu Chen
Qiu Chen
While collecting training data, even with the manual verification of experts from crowdsourcing platforms, eliminating incorrect annotations (noisy labels) completely is difficult and expensive. In dealing with datasets that contain noisy labels, over-parameterized deep neural networks (DNNs) tend to overfit, leading to poor generalization and classification performance. As a result, noisy label learning (NLL) has received significant attention in recent years. Existing research shows that although DNNs eventually fit all training data, they first prioritize fitting clean samples, then gradually overfit to noisy samples. Mainstream methods utilize this characteristic to divide training data but face two issues: class imbalance in the segmented data subsets and the optimization conflict between unsupervised contrastive representation learning and supervised learning. To address these issues, we propose a Balanced Partitioning and Training framework with Pseudo-Label Relaxed contrastive loss called BPT-PLR, which includes two crucial processes: a balanced partitioning process with a two-dimensional Gaussian mixture model (BP-GMM) and a semi-supervised oversampling training process with a pseudo-label relaxed contrastive loss (SSO-PLR). The former utilizes both semantic feature information and model prediction results to identify noisy labels, introducing a balancing strategy to maintain class balance in the divided subsets as much as possible. The latter adopts the latest pseudo-label relaxed contrastive loss to replace unsupervised contrastive loss, reducing optimization conflicts between semi-supervised and unsupervised contrastive losses to improve performance. We validate the effectiveness of BPT-PLR on four benchmark datasets in the NLL field: CIFAR-10/100, Animal-10N, and Clothing1M. Extensive experiments comparing with state-of-the-art methods demonstrate that BPT-PLR can achieve optimal or near-optimal performance.

5 December 2024 in PLOS ONE
Verified
Journal Article
Open access
PDF file
QZQian Zhang
Qian Zhang
YZYi Zhu
Yi Zhu
MYMing Yang
Ming Yang
GJGe Jin
Ge Jin
YZYingwen Zhu
Yingwen Zhu
QCQiu Chen
Qiu Chen
Deep neural networks have powerful memory capabilities, yet they frequently suffer from overfitting to noisy labels, leading to a decline in classification and generalization performance. To address this issue, sample selection methods that filter out potentially clean labels have been proposed. However, there is a significant gap in size between the filtered, possibly clean subset and the unlabeled subset, which becomes particularly pronounced at high-noise rates. Consequently, this results in underutilizing label-free samples in sample selection methods, leaving room for performance improvement. This study introduces an enhanced sample selection framework with an oversampling strategy (SOS) to overcome this limitation. This framework leverages the valuable information contained in label-free instances to enhance model performance by combining an SOS with state-of-the-art sample selection methods. We validate the effectiveness of SOS through extensive experiments conducted on both synthetic noisy datasets and real-world datasets such as CIFAR, WebVision, and Clothing1M. The source code for SOS will be made available at https://github.com/LanXiaoPang613/SOS.

30 June 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
YZYingwen Zhu
Yingwen Zhu
PLPing Li
Ping Li
QZQian Zhang
Qian Zhang
YZYi Zhu
Yi Zhu
JYJun Yang
Jun Yang
Clustering data streams has become a hot topic and has been extensively applied to many real-world applications. Compared with traditional clustering, data stream clustering is more challenging. Adaptive Resonance Theory (ART) is a powerful (online) clustering method, it can automatically adjust to learn both abstract and concrete information, and can respond to arbitrarily large non-stationary databases while having fewer parameters, low computational complexity, and less sensitivity to noise, but its limited feature representation hinders its application to complex data streams. In this paper, considering its advantages and disadvantages, we present its flexible extension for stream clustering, called fractional adaptive resonance theory (FRA-ART). FRA-ART enhances data representation by fractionally exponentiating input features using self-interactive basis functions (SIBFs) and incorporating feature interaction through cross-interactive basis functions (CIBFs) at the cost only of introducing an additionally adjustable fractional order. Both SIBFs and CIBFs can be precomputed using existing algorithms, making FRA-ART easily adaptable to any ART variant. Finally, comparative experiments on five data stream datasets, including artificial and real-world datasets, demonstrate FRA-ART’s superior robustness and comparable or improved performance in terms of accuracy, normalized mutual information, rand index, and cluster stability compared to ART and the state-of-the-art G-Stream algorithm.