检索结果-内蒙古大学图书馆

4th International Workshop on Human Brain and Artificial intelligence, HBAI 2024

作者： Cao, Siyuan Liang, Chuang Zhu, Qi Jiang, Rongtao Zhang, Daoqiang Calhoun, Vince D. Qi, Shile Department of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Brain-Machine Intelligence Technology Ministry of Education Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China Georgia State University Georgia Institute of Technology Emory University AtlantaGA United States Department of Radiology and Biomedical Imaging Yale University New HavenCT United States

ISBN: (纸本)9789819640003

Multimodal fusion offers a complementary perspective for understanding brain function and structure. Nevertheless, most existing multimodal fusion methods are unsupervised and thus ignore the diagnostic information. Previous supervised fusion models stack subjects from different diagnostic groups into a single feature matrix, resulting in potential interference between diagnostic groups. In this study, we propose a group-specific multimodal fusion method, called Group-specific Multiset Canonical Correlation analysis with Logistic Regression (GMCCALR) that can effectively leverage group specific information by incorporating a logistic regression term into mCCA and utilizing a group-specific fusion strategy. Results in human neuroimaging data show that GMCCALR provide higher diagnostic accuracy across several psychiatric disorders, including schizophrenia, schizoaffective disorder, bipolar disorder and autism spectrum disorder. We also show the identified disorder-specific multimodal patterns are replicable across multiple cohorts. Overall, results demonstrate the reliability and generalizability of the proposed GMCCALR approach and its efficacy for identifying multimodal co-varying diagnostic patterns for psychiatric disorders. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising

arXiv

引用

arXiv 2021年

作者： Wen, Chao Xu, Miao Zhang, Zhilin Zheng, Zhenzhe Wang, Yuhui Liu, Xiangyu Rong, Yu Xie, Dong Tan, Xiaoyang Yu, Chuan Xu, Jian Wu, Fan Chen, Guihai Zhu, Xiaoqiang Zheng, Bo MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China Shanghai Jiao Tong University China Alibaba Group China

In online advertising, auto-bidding has become an essential tool for advertisers to optimize their preferred ad performance metrics by simply expressing high-level campaign objectives and constraints. Previous works designed auto-bidding tools from the view of single-agent, without modeling the mutual influence between agents. In this paper, we instead consider this problem from a distributed multi-agent perspective, and propose a general Multi-Agent reinforcement learning framework for Auto-Bidding, namely MAAB, to learn the auto-bidding strategies. First, we investigate the competition and cooperation relation among auto-bidding agents, and propose a temperature-regularized credit assignment to establish a mixed cooperative-competitive paradigm. By carefully making a competition and cooperation trade-off among agents, we can reach an equilibrium state that guarantees not only individual advertiser’s utility but also the system performance (i.e., social welfare). Second, to avoid the potential collusion behaviors of bidding low prices underlying the cooperation, we further propose bar agents to set a personalized bidding bar for each agent, and then alleviate the revenue degradation due to the cooperation. Third, to deploy MAAB in the large-scale advertising system with millions of advertisers, we propose a mean-field approach. By grouping advertisers with the same objective as a mean auto-bidding agent, the interactions among the large-scale advertisers are greatly simplified, making it practical to train MAAB efficiently. Extensive experiments on the offline industrial dataset and Alibaba advertising platform demonstrate that our approach outperforms several baseline methods in terms of social welfare and revenue. Copyright © 2021, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Multilayer Maximum Spanning Tree Kernel For Brain Networks

A Multilayer Maximum Spanning Tree Kernel For Brain Networks

引用

IEEE International Symposium on Biomedical Imaging

作者： Xiaoxin Wang Xuyun Wen Kai Ma Daoqiang Zhang MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China

ISBN: (纸本)9781665412469;9781665429474

The brain network has been widely used for the construction of diverse brain disease diagnosis models. Among these models, an important and challenging task is how to quantify the network similarity. Although many graph kernels have been proposed for estimating topological similarity of a pair of networks, most of them ignore the global structure of networks by only focusing on subgraphs (i.e., a subset of original graph). To address this issue, we propose a novel multilayer graph kernel method based on maximum spanning tree (MST) for measuring the similarity of pair-wise brain networks. For two given networks, the proposed kernel estimates their similarity at each layer of MST generation to capture the topological properties of brain networks from local to global levels. Meanwhile, since the construction of MST is completely data-driven, MST based kernel can retain individual differences without destroying the individual inherent connectivity patterns. To validate our method, we apply our proposed graph kernel to the classifications of mild cognitive impairment (MCI). Experimental results demonstrate that our method outperforms the state-of-the-art graph kernel methods.

关键词： Focusing Biomedical measurement Nonhomogeneous media Brain modeling Medical diagnosis Kernel Task analysis

来源：评论

学校读者我要写书评

暂无评论

Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation

arXiv

引用

arXiv 2023年

作者： Wang, Chunyan Zhang, Dong Zhang, Liyan Tang, Jinhui The School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing211106 China

Thanks to the advantages of the friendly annotations and the satisfactory performance, Weakly-Supervised Semantic Segmentation (WSSS) approaches have been extensively studied. Recently, the single-stage WSSS was awakened to alleviate problems of the expensive computational costs and the complicated training procedures in multi-stage WSSS. However, results of such an immature model suffer from problems of background incompleteness and object incompleteness. We empirically find that they are caused by the insufficiency of the global object context and the lack of the local regional contents, respectively. Under these observations, we propose a single-stage WSSS model with only the image-level class label supervisions, termed as Weakly-Supervised Feature Coupling Network (WS-FCN), which can capture the multi-scale context formed from the adjacent feature grids, and encode the fine-grained spatial information from the low-level features into the high-level ones. Specifically, a flexible context aggregation module is proposed to capture the global object context in different granular spaces. Besides, a semantically consistent feature fusion module is proposed in a bottom-up parameter-learnable fashion to aggregate the fine-grained local contents. Based on these two modules, WS-FCN lies in a self-supervised end-to-end training fashion. Extensive experimental results on the challenging PASCAL VOC 2012 and MS COCO 2014 demonstrate the effectiveness and efficiency of WS-FCN, which can achieve state-of-the-art results by 65.02% and 64.22% mIoU on PASCAL VOC 2012 val set and test set, 34.12% mIoU on MS COCO 2014 val set, respectively. The code and weight have been released at: WS-FCN. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task

arXiv

引用

arXiv 2022年

作者： Feng, Quan Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing211106 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing211106 China

Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same, thus they can be utilized for learning across the tasks. While almost rare works explore the scenario where each task only has a small amount of training samples, and their label sets are just partially overlapped or even not. Learning such MTs is more challenging because of less correlation information available among these tasks. For this, we propose a framework to learn these tasks by jointly leveraging both abundant information from a learnt auxiliary big task with sufficiently many classes to cover those of all these tasks and the information shared among those partially-overlapped tasks. In our implementation of using the same neural network architecture of the learnt auxiliary task to learn individual tasks, the key idea is to utilize available label information to adaptively prune the hidden layer neurons of the auxiliary network to construct corresponding network for each task, while accompanying a joint learning across individual tasks. Our experimental results demonstrate its effectiveness in comparison with the state-of-the-art approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Rectified euler k-means and beyond

arXiv

引用

arXiv 2021年

作者： Lin, Yunxia Chen, Songcan College of Computer Science and Technology College of Artificial Intelligence Nanjing University of Aeronautics and Astronautics Nanjing211106 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence

Euler k-means (EulerK) first maps data onto the unit hyper-sphere surface of equi-dimensional space via a complex mapping which induces the robust Euler kernel and next employs the popular k-means. Consequently, besides enjoying the virtues of k-means such as simplicity and scalability to large data sets, EulerK is also robust to noises and outliers. Although so, the centroids captured by EulerK deviate from the unit hyper-sphere surface and thus in strict distributional sense, actually are outliers. This weird phenomenon also occurs in some generic kernel clustering methods. Intuitively, using such outlier-like centroids should not be quite reasonable but it is still seldom attended. To eliminate the deviation, we propose two Rectified Euler k-means methods, i.e., REK1 and REK2, which retain the merits of EulerK while acquire real centroids residing on the mapped space to better characterize the data structures. Specifically, REK1 rectifies EulerK by imposing the constraint on the centroids while REK2 views each centroid as the mapped image from a pre-image in the original space and optimizes these pre-images in Euler kernel induced space. Undoubtedly, our proposed REKs can methodologically be extended to solve problems of such a category. Finally, the experiments validate the effectiveness of REK1 and REK2. © 2021, CC BY.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Incremental Multi-Label Learning with Active Queries

引用

Journal of Computer Science & Technology 2020年第2期35卷 234-246页

作者： Sheng-Jun Huang Guo-Xiang Li Wen-Yu Huang Shao-Yuan Li College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China Key Laboratory of Pattern Analysis and Machine Intelligence Ministry of Industry and Information Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing University Nanjing 210023China

In multi-label learning,it is rather expensive to label instances since they are simultaneously associated with multiple ***,active learning,which reduces the labeling cost by actively querying the labels of the most valuable data,becomes particularly important for multi-label learning.A good multi-label active learning algorithm usually consists of two crucial elements:a reasonable criterion to evaluate the gain of querying the label for an instance,and an effective classification model,based on whose prediction the criterion can be accurately *** this paper,we first introduce an effective multi-label classification model by combining label ranking with threshold learning,which is incrementally trained to avoid retraining from scratch after every *** on this model,we then propose to exploit both uncertainty and diversity in the instance space as well as the label space,and actively query the instance-label pairs which can improve the classification model *** experiments on 20 datasets demonstrate the superiority of the proposed approach to state-of-the-art methods.

关键词： active learning multi-label learning uncertainty diversity

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Crowdsourcing Learning Based on Adversarial Consensus

Weakly Supervised Crowdsourcing Learning Based on Adversaria...

引用

International Conference on Computational Science and Computational intelligence (CSCI)

作者： Meng-Long Wei Shao-Yuan Li Sheng-Jun Huang Ministry of Industry and Information Technology 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)9781665458429

Crowdsourcing provides an efficient way to obtain labels for large datasets in the deep learning era. However, due to the non-expert workers, the annotations are usually ***, concerning the labeling cost, sparse annotations are common. To face this challenge, we propose an approach based on adversarial consensus, which trains one classifier for each worker, and enforces their predictions over the ground-truth labels to be maximally consistent by exploiting the generative adversarial learning idea. We give two implementations respectively for the light and heavy noise cases. Extensive experiments on real-world and synthetic datasets demonstrate the effectiveness of our approach.

关键词： Crowdsourcing Deep learning Costs Annotations Scientific computing Predictive models Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Survey

arXiv

引用

arXiv 2022年

作者： Ghojogh, Benyamin Ghodsi, Ali Karray, Fakhri Crowley, Mark Department of Electrical and Computer Engineering Machine Learning Laboratory University of Waterloo WaterlooON Canada Department of Statistics and Actuarial Science David R. Cheriton School of Computer Science Data Analytics Laboratory University of Waterloo WaterlooON Canada Department of Electrical and Computer Engineering Centre for Pattern Analysis and Machine Intelligence University of Waterloo WaterlooON Canada

This is a tutorial and survey paper on metric learning. Algorithms are divided into spectral, probabilistic, and deep metric learning. We first start with the definition of distance metric, Mahalanobis distance, and generalized Mahalanobis distance. In spectral methods, we start with methods using scatters of data, including the first spectral metric learning, relevant methods to Fisher discriminant analysis, Relevant Component analysis (RCA), Discriminant Component analysis (DCA), and the Fisher-HSIC method. Then, large-margin metric learning, imbalanced metric learning, locally linear metric adaptation, and adversarial metric learning are covered. We also explain several kernel spectral methods for metric learning in the feature space. We also introduce geometric metric learning methods on the Riemannian manifolds. In probabilistic methods, we start with collapsing classes in both input and feature spaces and then explain the neighborhood component analysis methods, Bayesian metric learning, information theoretic methods, and empirical risk minimization in metric learning. In deep learning methods, we first introduce reconstruction autoencoders and supervised loss functions for metric learning. Then, Siamese networks and its various loss functions, triplet mining, and triplet sampling are explained. Deep discriminant analysis methods, based on Fisher discriminant analysis, are also reviewed. Finally, we introduce multi-modal deep metric learning, geometric metric learning by neural networks, and few-shot metric learning. Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Can adversarial training be manipulated by non-robust features? 22

Can adversarial training be manipulated by non-robust featur...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Lue Tao Lei Feng Hongxin Wei Jinfeng Yi Sheng-Jun Huang Songcan Chen National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Chongqing University Chongqing China and RIKEN Center for Advanced Intelligence Project Japan Nanyang Technological University Singapore JD AI Research Beijing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9781713871088

Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. This defense ability, however, is challenged in this paper. We identify a novel threat model named stability attack, which aims to hinder robust availability by slightly manipulating the training data. Under this threat, we show that adversarial training using a conventional defense budget ε provably fails to provide test robustness in a simple statistical setting, where the non-robust features of the training data can be reinforced by ε-bounded perturbation. Further, we analyze the necessity of enlarging the defense budget to counter stability attacks. Finally, comprehensive experiments demonstrate that stability attacks are harmful on benchmark datasets, and thus the adaptive defense is necessary to maintain robustness.

关键词：

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：