检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qiao, Xiaoyu Li, Weisheng Xiao, Bin Huang, Yuping Yang, Lijian Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and Telecommunications Ministry of Education Chongqing China

Score matching with Langevin dynamics (SMLD) method has been successfully applied to accelerated MRI. However, the hyperparameters in the sampling process require subtle tuning, otherwise the results can be severely corrupted by hallucination artifacts, especially with out-of-distribution test data. To address the limitations, we proposed a novel workflow where naive SMLD samples serve as additional priors to guide model-driven network training. First, we adopted a pretrained score network to generate samples as preliminary guidance images (PGI), obviating the need for network retraining, parameter tuning and in-distribution test data. Although PGIs are corrupted by hallucination artifacts, we believe they can provide extra information through effective denoising steps to facilitate reconstruction. Therefore, we designed a denoising module (DM) in the second step to coarsely eliminate artifacts and noises from PGIs. The features are extracted from a score-based information extractor (SIE) and a cross-domain information extractor (CIE), which directly map to the noise patterns. Third, we designed a model-driven network guided by denoised PGIs (DGIs) to further recover fine details. DGIs are densely connected with intermediate reconstructions in each cascade to enrich the information and are periodically updated to provide more accurate guidance. Our experiments on different datasets reveal that despite the low average quality of PGIs, the proposed workflow can effectively extract valuable information to guide the network training, even with severely reduced training data and sampling steps. Our method outperforms other cutting-edge techniques by effectively mitigating hallucination artifacts, yielding robust and high-quality reconstruction results. Copyright © 2024, The Authors. All rights reserved.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

A Causal Disentangled Multi-Granularity Graph Classification Method

arXiv

引用

arXiv 2023年

作者： Li, Yuan Liu, Li Chen, Penggang Zhang, Youmin Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

Graph data widely exists in real life, with large amounts of data and complex structures. It is necessary to map graph data to low-dimensional embedding. Graph classification, a critical graph task, mainly relies on identifying the important substructures within the graph. At present, some graph classification methods do not combine the multi-granularity characteristics of graph data. This lack of granularity distinction in modeling leads to a conflation of key information and false correlations within the model. So, achieving the desired goal of a credible and interpretable model becomes challenging. This paper proposes a causal disentangled multi-granularity graph representation learning method (CDM-GNN) to solve this challenge. The CDM-GNN model disentangles the important substructures and bias parts within the graph from a multi-granularity perspective. The disentanglement of the CDM-GNN model reveals important and bias parts, forming the foundation for its classification task, specifically, model interpretations. The CDM-GNN model exhibits strong classification performance and generates explanatory outcomes aligning with human cognitive patterns. In order to verify the effectiveness of the model, this paper compares the three real-world datasets MUTAG, PTC, and IMDM-M. Six state-of-the-art models, namely GCN, GAT, Top-k, ASAPool, SUGAR, and SAT are employed for comparison purposes. Additionally, a qualitative analysis of the interpretation results is conducted. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

DPIC: decoupling prompt and intrinsic characteristics for LLM generated text detection 24

DPIC: decoupling prompt and intrinsic characteristics for LL...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xiao Yu Yuang Qi Kejiang Chen Guoqiang Chen Xi Yang Pengyuan Zhu Xiuwei Shang Weiming Zhang Nenghai Yu University of Science and Technology of China China and Key Laboratory of Cyberspace Security Ministry of Education China University of Science and Technology of China China Hefei High-dimensional Data Technology China

ISBN: (纸本)9798331314385

Large language models (LLMs) have the potential to generate texts that pose risks of misuse, such as plagiarism, planting fake reviews on e-commerce platforms, or creating inflammatory false tweets. Consequently, detecting whether a text is generated by LLMs has become increasingly important. Existing high-quality detection methods usually require access to the interior of the model to extract the intrinsic characteristics. However, since we do not have access to the interior of the black-box model, we must resort to surrogate models, which impacts detection quality. In order to achieve high-quality detection of black-box models, we would like to extract deep intrinsic characteristics of the black-box model generated texts. We view the generation process as a coupled process of prompt and intrinsic characteristics of the generative model. Based on this insight, we propose to decouple prompt and intrinsic characteristics (DPIC) for LLM-generated text detection method. Specifically, given a candidate text, DPIC employs an auxiliary LLM to reconstruct the prompt corresponding to the candidate text, then uses the prompt to regenerate text by the auxiliary LLM, which makes the candidate text and the regenerated text align with their prompts, respectively. Then, the similarity between the candidate text and the regenerated text is used as a detection feature, thus eliminating the prompt in the detection process, which allows the detector to focus on the intrinsic characteristics of the generative model. Compared to the baselines, DPIC has achieved an average improvement of 6.76% and 2.91% in detecting texts from different domains generated by GPT-4 and Claude3, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Defense Framework for Backdoor Attacks in Federated Learning Based on Client-Server Detection 4

A Defense Framework for Backdoor Attacks in Federated Learni...

引用

4th International Conference on Industrial Automation, Robotics and Control Engineering, IARCE 2024

作者： Chen, Ding Li, Tianrui Yu, Cai Al-Huthaifi, Rasha Huang, Wei School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China School of Cybersecurity Chengdu University of Information Technology Sichuan Provincial Key Laboratory of Cyberspace Security Chengdu610225 China School of Cybersecurity Chengdu University of Information Technology Chengdu610225 China College of Computer and Data Science Fuzhou University Fuzhou350108 China

ISBN: (纸本)9798350380323

Addressing the challenge of backdoor attacks in federated learning (FL), various defense schemes are examined, resulting in the proposal of a comprehensive strategy that incorporates both client-side and server-side measures. This defense strategy is based on Dropout and LOF (Local Outlier Factor) outlier detection techniques. The model's resilience against data poisoning is enhanced by applying the Dropout technique on the client side. At the same time, the LOF outlier detection algorithm is utilized on the server side to identify potential abnormal model updates. Experimental results highlight the effectiveness of the proposed strategy, demonstrating a significant reduction in the Attack Success Rate (ASR) from 88.11% to 1.62% on the FMNIST dataset, and from 95.45% to only 0.25% on the EMNIST dataset. The success rate of backdoor attacks is notably diminished, confirming the strategy's strong backdoor defense capabilities. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Preface: Brain-Inspired AI Research

引用

Science China(Technological Sciences) 2024年第8期67卷 2281-2281页

作者： GONG YiHong WANG GuoYin College of Artificial Intelligence Xi’an Jiaotong UniversityXi’an 710049China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing400065China College of Computer and Information Science Chongqing Normal UniversityChongqing401331China

Large AGI (artificial general intelligence) models, represented by OpenAI’s GPT-4, DALL-E, Sora, etc., have amazed the world by exhibiting superior capabilities on a variety of NLP and text-to-image/video generation tasks. The success of these models was achieved by exploiting ultra-scale training data, ultra-scale computational models, and unlimited computing *** brute force approach, however, is not only making an adverse impact on global warming prevention, but also raising skepticism on whether such a development path can really achieve true AGI systems. Recently, there have been increasing scientific studies that report the delusion phenomenon of the AGI models, mainly caused by their inability to learn correct knowledge and correct world models.

关键词： artificial Open knowledge

来源：评论

学校读者我要写书评

暂无评论

Optimal Scheduling for Integrated Energy System via Model-Based Reinforcement Learning 24

Optimal Scheduling for Integrated Energy System via Model-Ba...

引用

2024 International Conference on Artificial Intelligence of Things and Computing, AITC 2024

作者： Cheng, Kexin Wan, Jianxiong Liu, Chuyi Sun, Pengfei Li, Leixiao Zhang, Huaqin School of Data Science and Application Inner Mongolia University of Technology Inner Mongolia Autonomous Region Hohhot China Inner Mongolia Key Laboratory of Beijiang Cyberspace Security Inner Mongolia Autonomous Region Hohhot China Research Center of Large-Scale Energy Storage Technologies Ministry of Education of the People's Republic of China Inner Mongolia Autonomous Region Hohhot China

ISBN: (纸本)9798400709869

The Integrated Energy System (IES) integrates energy consumption, conversion, and storage to increase the utilization of renewable energy sources and fossil fuels. When using heuristic algorithms and mathematical optimization methods for optimal scheduling of IES, these methods often face challenges of high computational cost and insufficient model accuracy, for which Reinforcement Learning (RL) offers a promising solution. However, most studies have used Model-Free Reinforcement Learning (MFRL) for optimal scheduling, which is limited by problems of low sampling efficiency and long training time. Model-Based Reinforcement Learning (MBRL) is an effective alternative to accelerate learning and facilitate RL applications. Therefore, this paper compares the performance gap between MFRL and MBRL in the optimal scheduling problem of IES to determine the superiority of MBRL. Experimental results show that the MBPO algorithm significantly improves sampling efficiency and learning speed at high prediction accuracy, outperforming the Soft Actor-Critic (SAC) algorithm. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

The Research on V2V Cooperative Caching Method Based on Vehicle Attributes 24

The Research on V2V Cooperative Caching Method Based on Vehi...

引用

2024 International Conference on Artificial Intelligence of Things and Computing, AITC 2024

作者： Wang, Zirui Wang, Hui Wan, Jianxiong Liu, Chuyi Sun, Pengfei Li, Leixiao School of Data Science and Application Inner Mongolia University of Technology Inner Mongolia Autonomous Region Hohhot China Inner Mongolia Key Laboratory of Beijiang Cyberspace Security Inner Mongolia Autonomous Region Hohhot China Research Center of Large-Scale Energy Storage Technologies Ministry of Education of the People's Republic of China Inner Mongolia Autonomous Region Hohhot China

ISBN: (纸本)9798400709869

To address the increasingly severe issue of insufficient vehicular caching in the Internet of Vehicles (IoV), Vehicular edge computing uses base stations (BS) and vehicles with computing and storage capabilities as edge servers to cache content. However, most existing studies focus on reducing task costs, assuming vehicles can simultaneously act as requesters and providers, without considering whether a vehicle is suitable to serve as a provider, willing to share resources or ensure secure data transmission, thus lowering matching efficiency. Deep reinforcement learning and blockchain technology were integrated into the Internet of Vehicles to address distributed vehicle-to-vehicle collaborative caching. An optimal collaborative caching strategy was designed, considering dynamic vehicle attributes, with the system's objective being to maximize vehicle utility to encourage resource sharing. Simulation results confirm that the proposed blockchain-based vehicular edge computing collaborative caching scheme with deep reinforcement learning significantly outperforms other strategies. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

GBFRS: Robust Fuzzy Rough Sets via Granular-ball Computing

arXiv

引用

arXiv 2025年

作者： Xia, Shuyin Lian, Xiaoyu Sang, Binbin Wang, Guoyin Gao, Xinbo Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China College of Computer and Information Science the National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing401331 China

Fuzzy rough set theory is effective for processing datasets with complex attributes, supported by a solid mathematical foundation and closely linked to kernel methods in machine learning. Attribute reduction algorithms and classifiers based on fuzzy rough set theory exhibit promising performance in the analysis of high-dimensional multivariate complex data. However, most existing models operate at the finest granularity, rendering them inefficient and sensitive to noise, especially for high-dimensional big data. Thus, enhancing the robustness of fuzzy rough set models is crucial for effective feature selection. Muiti-garanularty granular-ball computing, a recent development, uses granular-balls of different sizes to adaptively represent and cover the sample space, performing learning based on these granular-balls. This paper proposes integrating multi-granularity granular-ball computing into fuzzy rough set theory, using granular-balls to replace sample points. The coarse-grained characteristics of granular-balls make the model more robust. Additionally, we propose a new method for generating granular-balls, scalable to the entire supervised method based on granular-ball computing. A forward search algorithm is used to select feature sequences by defining the correlation between features and categories through dependence functions. Experiments demonstrate the proposed model’s effectiveness and superiority over baseline methods. The source codes and datasets are both available on the public link: https://***/lianxiaoyu724/GBFRS Copyright © 2025, The Authors. All rights reserved.

关键词： Granular computing

来源：评论

学校读者我要写书评

暂无评论

Federated Hybrid-Supervised Learning for Universal Medical Image Segmentation

Federated Hybrid-Supervised Learning for Universal Medical I...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shenhai Zheng Sian Wen Congyu Li Qing Chen Laquan Li College of Computer Science and Technology Chongqing University of Posts and Telecommunications China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education China School of Science Chongqing University of Posts and Telecommunications China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL faces difficulties with heterogeneous data and limited annotations in medical image segmentation. Motivated by this discovery, this study proposes a novel hybrid-supervised federated learning method (FedSLAG) that explores various types of annotations in medical imaging. To focus more on weakly-supervised and unsupervised scenarios within hybrid-supervised learning, a federated Gaussian enhancement module was proposed for heterogeneous sparse annotations (points and scribbles). The feature extraction module combines the features of multiple weakly-supervised clients and establishes the correlation of similar pixels, thus making up for the deficiency of scarce annotations and the insufficient feature extraction capability of a single machine. Then, a two-stage broadcast mechanism based on supervision sparsity was proposed to alleviate optimization deviation in local models. Experiments on breast tumor and skin lesion segmentation tasks demonstrate significant efficiency gains as well as highly competitive segmentation accuracy in many hybrid-supervised situations. Our codes are available at: https://***/TrivenDev/FedSLAG.

关键词： Training Image segmentation Breast tumors Annotations Federated learning Feature extraction Skin Lesions Speech processing Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A granular-ball generation method based on local density for classification

引用

Information Sciences 2025年 717卷

作者： Liu, Fan Zhang, Qinghua Xia, Shuyin Xie, Qin Liao, Wei Zhang, Siyang School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunication Chongqing400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing400065 China Tourism Multi-source Data Perception and Decision Technology Key Laboratory of the Ministry of Culture and Tourism Chongqing400065 China

As a new branch of granular computing, granular-ball computing (GBC) has become increasingly popular due to its high efficiency, robustness, and scalability. However, in classification tasks, the existing mainstream methods for generating granular-ball (GB) have two common issues: GBs generated by the existing methods are not accurate enough to describe the distribution of the original data and there are de-overlap operations in the existing GB generation process, which increase the workload of the GB generation process. Therefore, to solve the above two issues, a GB generation method based on local density (LDGBG) is proposed in this paper. First, centers of GBs are selected based on local density to ensure the generated GBs are more consistent with the original data distribution. Second, the method for calculating radii avoids overlaps and incorporates the idea of compact within class and decentralized between classes, which will improve classification performance. Furthermore, a sparsity index is introduced to assess the sparsity of datasets, thereby enabling more effective utilization of original samples in sparse datasets. Finally, comparative experiments are conducted on 27 benchmark datasets and the experimental results show that LDGBG is superior to the existing mainstream models in effectiveness and robustness. © 2025 Elsevier Inc.

关键词： Classification Granular computing Granular-ball computing Granular-ball generation Local density

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：