检索结果-内蒙古大学图书馆

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Wang, Xinrui Wan, Wenhai Geng, Chuanxing Li, Shaoyuan Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

ISBN: (纸本)9781713899921

Learning binary classifiers from positive and unlabeled data (PUL) is vital in many real-world applications, especially when verifying negative examples is difficult. Despite the impressive empirical performance of recent PUL methods, challenges like accumulated errors and increased estimation bias persist due to the absence of negative labels. In this paper, we unveil an intriguing yet long-overlooked observation in PUL: resampling the positive data in each training iteration to ensure a balanced distribution between positive and unlabeled examples results in strong early-stage performance. Furthermore, predictive trends for positive and negative classes display distinctly different patterns. Specifically, the scores (output probability) of unlabeled negative examples consistently decrease, while those of unlabeled positive examples show largely chaotic trends. Instead of focusing on classification within individual time frames, we innovatively adopt a holistic approach, interpreting the scores of each example as a temporal point process (TPP). This reformulates the core problem of PUL as recognizing trends in these scores. We then propose a novel TPP-inspired measure for trend detection and prove its asymptotic unbiasedness in predicting changes. Notably, our method accomplishes PUL without requiring additional parameter tuning or prior assumptions, offering an alternative perspective for tackling this problem. Extensive experiments verify the superiority of our method, particularly in a highly imbalanced real-world setting, where it achieves improvements of up to 11.3% in key metrics. The code is available at https://***/wxr99/HolisticPU. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

An Improved AdaBoost Method in Imbalanced Data Learning

An Improved AdaBoost Method in Imbalanced Data Learning

引用

2023 International Conference on Cyber-Physical Social intelligence, ICCSI 2023

作者： Li, Ting Chen, Xiaofeng Li, Weikai Chongqing Jiaotong University Department of Mathematics Chongqing China Miit Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (纸本)9798350312492

Learning from imbalanced datasets has recently received increasing research attention. Despite the remarkable results of AdaBoost in balanced situation, the imbalance problem remains to be solved. To address this, this paper proposes a novel method to improve the AdaBoost using a new error factor and a weighted voting parameter for a few classes and weak classifiers. Our method can weaken the dominant role of the majority class in iterative training by improving the classification ability of the minority class. The superiority of the proposed algorithm is finally proved theoretically and practically. Several real-world imbalance datasets in experiments as specific support, and our method outperforms previous algorithms, especially in the F-1 metric. © 2023 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Robust AUC maximization for classification with pairwise confidence comparisons

引用

Frontiers of Computer Science 2024年第4期18卷 73-83页

作者： Haochen SHI Mingkun XIE Shengjun HUANG College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing 211106China

Supervised learning often requires a large number of labeled examples,which has become a critical bottleneck in the case that manual annotating the class labels is *** mitigate this issue,a new framework called pairwise comparison(Pcomp)classification is proposed to allow training examples only weakly annotated with pairwise comparison,i.e.,which one of two examples is more likely to be *** previous study solves Pcomp problems by minimizing the classification error,which may lead to less robust model due to its sensitivity to class *** this paper,we propose a robust learning framework for Pcomp data along with a pairwise surrogate loss called *** provides an unbiased estimator to equivalently maximize AUC without accessing the precise class ***,we prove the consistency with respect to AUC and further provide the estimation error bound for the proposed *** studies on multiple datasets validate the effectiveness of the proposed method.

关键词： method pairwise weakly

来源：评论

学校读者我要写书评

暂无评论

Medical Report Generation Based on Segment-Enhanced Contrastive Representation Learning 12th

Medical Report Generation Based on Segment-Enhanced Contras...

引用

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Zhao, Ruoqing Wang, Xi Dai, Hongliang Gao, Pan Li, Piji College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (纸本)9783031446955

Automated radiology report generation has the potential to improve radiology reporting and alleviate the workload of radiologists. However, the medical report generation task poses unique challenges due to the limited availability of medical data and the presence of data bias. To maximize the utility of available data and reduce data bias, we propose MSCL (Medical image Segmentation with Contrastive Learning), a framework that utilizes the Segment Anything Model (SAM) to segment organs, abnormalities, bones, etc., and can pay more attention to the meaningful ROIs in the image to get better visual representations. Then we introduce a supervised contrastive loss that assigns more weight to reports that are semantically similar to the target while training. The design of this loss function aims to mitigate the impact of data bias and encourage the model to capture the essential features of a medical image and generate high-quality reports. Experimental results demonstrate the effectiveness of our proposed model, where we achieve state-of-the-art performance on the IU X-Ray public dataset. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

Sign-aware Perturbations Regression

Sign-aware Perturbations Regression

引用

2021 SIAM International Conference on Data Mining, SDM 2021

作者： Li, Zhongnian Zhang, Tao Shao, Wei Chen, Songcan Zhang, Daoqiang MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9781611976700

This paper presents the first study on Sign-aware Perturbations Regression (SaPR), where the observed response variables contain the aware sign (negative or positive) perturbations. In order to predict the non-perturbation response variables, we propose a novel parameter estimator SZOM (i.e.,Setting Zero Operator Method), which aims at taking full advantage of the aware perturbations information to correct the mistake values in the estimation process with computationally efficiency. In this paper, the two aspects of theoretical analysis are proposed to deeply understand our method. Firstly, we establish the perturbation parameter error upper bound and prove consistency guarantee in the linear regression scenario. Secondly, we introduce the generalization error bound for the proposed SZMO, which indicates that the error bound is related to the value and the number of negative and positive perturbations. The effectiveness of the proposed approach is well validated by the experimental results on both synthetic and real datasets. © 2021 by SIAM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph Hyperalignment for Multi-subject fMRI Functional Alignment 1

引用

1st International Workshop on Graph Learning in Medical Imaging, GLMI 2019 held in conjunction with the 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2019

作者： Li, Weida Chen, Fang Zhang, Daoqiang College of Computer Science and Technology MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (数字)9783030358174

ISBN: (纸本)9783030358167

In fMRI analysis, the scientist seeks to aggregate multi-subject fMRI data so that inferences shared across subjects can be achieved. The challenge is to eliminate the variability of anatomical structure and functional topography of the human brain, which calls for aligning fMRI data across subjects. However, the existing methods do not exploit the geometry of the stimuli, which can be inferred by using certain domain knowledge and then serve as a priori. In this paper, such geometry is encoded in a graph matrix, and we propose an algorithm named Graph Hyperalignment for leveraging it. Specifically, a kernel-based optimization is developed to allow for non-linear feature extraction. To tackle overfitting caused by the high-spatial-and-low-temporal resolution of fMRI, the data in the new feature space are assumed to lie in a low-dimensional affine subspace, which can be implicitly integrated into the proposed optimization. Unlike other iterative existing methods, GHA reaches an optimal solution directly. Examining over four real datasets, Graph Hyperaligment achieves superior results to other methods. © 2019, Springer Nature Switzerland AG.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Adaptive Joint Attention with Reinforcement Training for Convolutional Image Caption 1st

Adaptive Joint Attention with Reinforcement Training for C...

引用

1st International Workshop on Human Brain and Artificial intelligence, HBAI 2019, held in conjunction with the 28th International Joint Conference on Artificial intelligence, IJCAI 2019

作者： Chen, Ruoyu Li, Zhongnian Zhang, Daoqiang College of Computer Science and Technology MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9789811513978

A convolutional decoder for image caption has proven to be easier to train than the Long Short Term Memory (LSTM) decoder [2]. However, previous convolutional image captioning methods are not good at capture the relationship between generated words, which could lead to failure in predicting visually unrelated words. To address this issue, we propose an Adaptive Joint Attention (AJA) module for the convolutional decoder, by incorporating self-attention to explore the correlation between generated words automatically. Specifically, we develop a word gate with multi-head self-attention to directly capture words’ relationship. An adaptive combination strategy is proposed to learn which word is less related to image information. Besides, reinforcement learning is applied for directly optimizing the non-differentiable metrics while avoiding the exposure bias during inference. Extensive evaluations on two public data sets demonstrate that our method outperforms several state-of-the-art approaches in image captioning task. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Detecting differential transcript usage across multiple conditions for RNA-seq data based on the smoothed LDA model

引用

Frontiers of Computer Science 2021年第3期15卷 217-219页

作者： Jing LI Xuejun LIU Daoqiang ZHANG College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsMIIT Key Laboratory of Pattern Analysis and Machine IntelligenceNanjing 211106China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 210023China

1 Introduction and main contributions Differential transcript usage(DTU),which refers to the event that the relative transcript abundance within a gene changes between *** detect DTU,various methods have been proposed,which can be classified into exon-based models and gene-based *** approaches either cannot estimate the relative transcript abundance,or they cannot deal properly with the multi-source mapping problems of ***,few methods currently consider sample-to-sample variability under multiple conditions[1].

关键词： conditions. properly differential

来源：评论

学校读者我要写书评

暂无评论

Boundary Data Augmentation for Offline Reinforcement Learning

引用

ZTE Communications 2023年第3期21卷 29-36页

作者： SHEN Jiahao JIANG Ke TAN Xiaoyang College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing 211106China

Offline reinforcement learning(ORL)aims to learn a rational agent purely from behavior data without any online *** of the major challenges encountered in ORL is the problem of distribution shift,i.e.,the mismatch between the knowledge of the learned policy and the reality of the underlying *** works usually handle this in a too pessimistic manner to avoid out-of-distribution(OOD)queries as much as possible,but this can influence the robustness of the agents at unseen *** this paper,we propose a simple but effective method to address this *** key idea of our method is to enhance the robustness of the new policy learned offline by weakening its confidence in highly uncertain regions,and we propose to find those regions by simulating them with modified Generative Adversarial Nets(GAN)such that the generated data not only follow the same distribution with the old experience but are very difficult to deal with by themselves,with regard to the behavior policy or some other reference *** then use this information to regularize the ORL algorithm to penalize the overconfidence behavior in these *** experiments on several publicly available offline RL benchmarks demonstrate the feasibility and effectiveness of the proposed method.

关键词： offline reinforcement learning out‐of‐distribution state robustness uncertainty

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Multi-Hop Graph Convolution Network for Predicting Fluid intelligence via Functional Connectivity

A Multi-Scale Multi-Hop Graph Convolution Network for Predic...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Wen, Xuyun Cao, Qumei Zhang, Daoqiang Nanjing University of Aeronautics and Astronautics Nanjing College of Computer Science and Technology MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Jiangsu China

ISBN: (纸本)9781665468190

Predicting fluid intelligence via neuroimaging data is important to understand neural mechanisms underlying diverse complex cognitive tasks in human brain. Functional connectivity (FC) reflects interactions among brain regions providing rich information of brain organization, which has been widely used in various behavior predictions. With the success of deep neural networks, graph convolutional network (GCN) is regarded as a promising feature learning method in FC networks (FCNs). However, as a challenging task, the existing GCN models cannot achieve a satisfactory performance in fluid intelligence predication due to the insufficient information utilization of brain connectivity and the limitation of graph convolution layer. To tackle these problems, this paper developed a Multi-Scale Multi-Hop GCN (MS-MH-GCN) to estimate fluid intelligence score by using FC. In the proposed method, we considered the hierarchy of brain system and thus utilized FCs from multiple spatial scales as input for the subsequent feature learning to achieve a complete characterize of brain organization for each individual. We also designed a new multi-hop graph convolution layer that uses multi-hop neighbors instead of l-hop neighbor in traditional GCN to guide message passing of nodal feature at every step. The introduction of high-order graph information benefits to the model learning ability improvement. Additionally, it is also worth emphasizing that, during feature learning process, we added contrast constraint to multi-scale FCNs to improve the similarity of feature representations across different spatial scales within a subject. Experimental results showed that our proposed method performed much better than the other four art-of-the-state methods. © 2022 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：