检索结果-内蒙古大学图书馆

Robust Federated Semi-Supervised Learning for Medical Image Classification via Pseudo-Label Filtering

学校读者我要写书评

暂无评论

Robust Federated Semi-Supervised Learning for Medical Image ...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ziwei Wang Shuyu Guo Mingzhu Zhu Tian Bai College of Software Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Federated learning (FL) enables collaborative model training across multiple medical institutions to ensure data security. However, due to the variations in medical imaging equipment and regions at different medical institutions, FL methods usually suffer from insufficient data annotations and irrelevant noise within private datasets. To address these issues, a robust federated semi-supervised learning method via pseudo-label filtering (PFRFed) is introduced to utilize unlabeled data while mitigating the impact of noise data. Compared with existing federated semi-supervised learning methods, we propose a pseudo-label filtering mechanism with double dynamic thresholds, which allows the model to adopt more unlabeled data by adjusting the confidence and entropy thresholds at each stage of model training. Moreover, to reduce the degradation caused by noise data in private datasets from different clients, a noise-tolerant loss function and a grouping aggregation method based on the local model similarity are employed. The comparative experiments demonstrate the effectiveness of PFRFed, which has achieved the best classification accuracy of 95.20% and 88.72% on two public medical datasets. Also, PFRFed exhibits heightened resilience to variations in noisy data ratio and labeled data ratio, reaffirming its versatility and robustness.

关键词： Training Filtering Biological system modeling Noise Semisupervised learning Data models Robustness Noise measurement Biomedical imaging Image classification

Uncertainty-Aware Global-View Reconstruction for Multi-View Multi-Label Feature Selection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hao, Pingting Liu, Kunpeng Gao, Wanfu College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Computer Science Portland State University PortlandOR97201 United States

In recent years, multi-view multi-label learning (MVML) has gained popularity due to its close resemblance to real-world scenarios. However, the challenge of selecting informative features to ensure both performance and efficiency remains a significant question in MVML. Existing methods often extract information separately from the consistency part and the complementary part, which may result in noise due to unclear segmentation. In this paper, we propose a unified model constructed from the perspective of global-view reconstruction. Additionally, while feature selection methods can discern the importance of features, they typically overlook the uncertainty of samples, which is prevalent in realistic scenarios. To address this, we incorporate the perception of sample uncertainty during the reconstruction process to enhance trustworthiness. Thus, the global-view is reconstructed through the graph structure between samples, sample confidence, and the view relationship. The accurate mapping is established between the reconstructed view and the label matrix. Experimental results demonstrate the superior performance of our method on multi-view datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature Selection

Improved CS Algorithm and its Application in Parking Space Prediction

学校读者我要写书评

暂无评论

Journal of Bionic engineering 2020年第5期17卷 1075-1083页

作者： Rui Guo Xuanjing Shen Hui Kang College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun 130012China

This paper simulates the cuckoo incubation process and flight path to optimize the Wavelet Neural Network(WNN)model,and proposes a parking prediction algorithm based on WNN and improved Cuckoo Search(CS)***,the initialization parameters are provided to optimize the WNN using the improved *** traditional CS algorithm adopts the strategy of overall update and evaluation,but does not consider its own information,so the convergence speed is very *** proposed algorithm employs the evaluation strategy of group update,which not only retains the advantage of fast convergence of the dimension-by-dimension update evaluation strategy,but also increases the mutual relationship between the nests and reduces the overall running ***,we use the WNN model to predict parking *** proposed algorithm is compared with six different heuristic algorithms in five *** experimental results show that the proposed algorithm is superior to other algorithms in terms of running time and accuracy.

关键词： wavelet neural network cuckoo search algorithm available parking spaces prediction bionic

WHO IS YOUR RIGHT MIXUP PARTNER IN POSITIVE AND UNLABELED LEARNING 10

学校读者我要写书评

暂无评论

WHO IS YOUR RIGHT MIXUP PARTNER IN POSITIVE AND UNLABELED LE...

1.th International Conference on Learning Representations, ICLR 2022

作者： Li, Changchun Li, Ximing Feng, Lei Ouyang, Jihong College of Computer Science and Technology Jilin University China College of Computer Science Chongqing University China Imperfect Information Learning Team RIKEN Center for Advanced Intelligence Project Japan Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China

Positive and Unlabeled (PU) learning targets inducing a binary classifier from weak training datasets of positive and unlabeled instances, which arise in many real-world applications. In this paper, we propose a novel PU learning method, namely Positive and unlabeled learning with Partially Positive Mixup (P3Mix), which simultaneously benefits from data augmentation and supervision correction with a heuristic mixup technique. To be specific, we take inspiration from the decision boundary deviation phenomenon observed in our preliminary experiments, where the learned PU boundary tends to deviate from the fully supervised boundary towards the positive side. For the unlabeled instances with ambiguous predictive results, we select their mixup partners from the positive instances around the learned PU boundary, so as to transform them into augmented instances near to the boundary yet with more precise supervision. Accordingly, those augmented instances may push the learned PU boundary towards the fully supervised boundary, thereby improving the classification performance. Comprehensive experimental results demonstrate the effectiveness of the heuristic mixup technique in PU learning and show that P3Mix can consistently outperform the state-of-the-art PU learning methods. © 2022 ICLR 2022 - 1.th International Conference on Learning Representationss. All rights reserved.

关键词： Heuristic methods

Reconsidering Feature Structure Information and Latent Space Alignment in Partial Multi-label Feature Selection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pan, Hanlin Liu, Kunpeng Gao, Wanfu College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Computer Science Portland State University PortlandOR97201 United States

The purpose of partial multi-label feature selection is to select the most representative feature subset, where the data comes from partial multi-label datasets that have label ambiguity issues. For label disambiguation, previous methods mainly focus on utilizing the information inside the labels and the relationship between the labels and features. However, the information existing in the feature space is rarely considered, especially in partial multi-label scenarios where the noises is considered to be concentrated in the label space while the feature information is correct. This paper proposes a method based on latent space alignment, which uses the information mined in feature space to disambiguate in latent space through the structural consistency between labels and features. In addition, previous methods overestimate the consistency of features and labels in the latent space after convergence. We comprehensively consider the similarity of latent space projections to feature space and label space, and propose new feature selection term. This method also significantly improves the positive label identification ability of the selected features. Comprehensive experiments demonstrate the superiority of the proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature extraction

Dpdn: A Novel Approach to Mbd with Multiple Observations

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Tai, Ran Ouyang, Dantong Liu, Weiting Zhang, Liming College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China

Model-based diagnosis (MBD) with multiple abnormal observations poses a significant challenge. To address this, we propose the Dual Principles with Decision Node (DPDN) algorithm. DPDN encompasses two novel principles: Output Dependency Judgment Principle (ODJP) and Deep Propagation Dependency Principle (DPDP), aimed at identifying a larger portion of'normal components, thus expanding the concept of filtered nodes and enhancing diagnostic efficiency. The second part of DPDN introduces a new decision node guided by its Decision Node Principle (DNP), which further aids the diagnostic process by categorizing additional components as normal. This inclusion significantly reduces the number of components to be considered, thereby improving diagnostic efficiency. DPDN provides a robust solution to MBD complexities with multiple observations, offering quicker diagnoses with remarkable efficiency. Comparative experiments on ISCAS'85 and ITC'99 benchmarks were conducted to evaluate DPDN against other methods. The results distinctly highlight DPDN's superior performance compared to algorithms like HSD, IHSD, and DiagDO. © 2023, The Authors. All rights reserved.

关键词： Efficiency

Symmetric Transformer-based Network for Unsupervised Image Registration

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ma, Mingrui Song, Lei Xu, Yuanbo Liu, Guixia Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University China

Medical image registration is a fundamental and critical task in medical image analysis. With the rapid development of deep learning, convolutional neural networks (CNN) have dominated the medical image registration field. Due to the disadvantage of the local receptive field of CNN, some recent registration methods have focused on using transformers for non-local registration. However, the standard Transformer has a vast number of parameters and high computational complexity, which causes Transformer can only be applied at the bottom of the registration models. As a result, only coarse information is available at the lowest resolution, limiting the contribution of Transformer in their models. To address these challenges, we propose a convolution-based efficient multi-head self-attention (CEMSA) block, which reduces the parameters of the traditional Transformer and captures local spatial context information for reducing semantic ambiguity in the attention mechanism. Based on the proposed CEMSA, we present a novel Symmetric Transformer-based model (SymTrans). SymTrans employs the Transformer blocks in the encoder and the decoder respectively to model the long-range spatial cross-image relevance. We apply SymTrans to the displacement field and diffeomorphic registration. Experimental results show that our proposed method achieves state-of-the-art performance in image registration. Copyright © 2022, The Authors. All rights reserved.

关键词： Image registration

Label-Guided Graph Contrastive Learning for Semi-Supervised Node Classification

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Peng, Meixin Juan, Xin Li, Zhanshan College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China

Semi-supervised node classification is a task of predicting the labels of unlabeled nodes using limited labeled nodes and numerous unlabeled nodes. Recently, Graph Neural Networks (GNNs) have achieved remarkable success in this task. However, existing GNNs models typically have shallow architectures and only consider labeled nodes and their low-order neighbors during training. As a result, the supervision signals from the massive unlabeled nodes remain underutilized. To address this limitation, graph contrastive learning has been applied in semi-supervised node classification, which pulls together positive nodes and pushes away negative nodes in the embedding space. Nevertheless, existing node-level contrastive learning methods usually sample the same node in different augmented views as positive nodes and all other nodes as negative nodes. Consequently, many semantically similar nodes are not sampled as positive nodes but are mistakenly sampled as negative nodes. To tackle this issue, we propose a novel Label-guided Graph Contrastive Learning~(LGGCL) training algorithm for semi-supervised node classification. Specifically, we first propose a Label-guided Graph Contrastive Learning framework as the basis of LGGCL training algorithm. Then we incorporate a self-checking mechanism based on deep clustering to ensure the authenticity of the sampled positive nodes. Moreover, we design a reweighting strategy based on the probability distribution of the anchor node to enhance the effect of hard negative nodes. Finally, experimental results on various graph benchmarks demonstrate the superiority of LGGCL compared to other state-of-the-art approaches. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

Joint Scheduling and Trajectory Optimization of Charging UAV in Wireless Rechargeable Sensor Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yanheng Pan, Hongyang Sun, Geng Wang, Aimin Li, Jiahui Liang, Shuang College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China

Wireless rechargeable sensor networks with a charging unmanned aerial vehicle (CUAV) have the broad application prospects in the power supply of the rechargeable sensor nodes (SNs). However, how to schedule a CUAV and design the trajectory to improve the charging efficiency of the entire system is still a vital problem. In this paper, we formulate a joint-CUAV scheduling and trajectory optimization problem (JSTOP) to simultaneously minimize the hovering points of CUAV, the number of the repeatedly covered SNs and the flying distance of CUAV for charging all SNs. Due to the complexity of JSTOP, it is decomposed into two optimization subproblems that are CUAV scheduling optimization problem (CSOP) and CUAV trajectory optimization problem (CTOP). CSOP is a hybrid optimization problem that consists of the continuous and discrete solution space, and the solution dimension in CSOP is not fixed since it should be changed with the number of hovering points of CUAV. Moreover, CTOP is a completely discrete optimization problem. Thus, we propose a particle swarm optimization (PSO) with a flexible dimension mechanism, a K-means operator and a punishment-compensation mechanism (PSOFKP) and a PSO with a discretization factor, a 2-opt operator and a path crossover reduction mechanism (PSOD2P) to solve the converted CSOP and CTOP, respectively. Simulation results evaluate the benefits of PSOFKP and PSOD2P under different scales and settings of the network, and the stability of the proposed algorithms is verified. Copyright © 2023, The Authors. All rights reserved.

关键词： Sensor nodes