检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Huang, Wei-Jin Li, Yuan-Ming Xia, Zhi-Wei Tang, Yu-Ming Lin, Kun-Yu Hu, Jian-Fang Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology China

Error detection in procedural activities is essential for consistent and correct outcomes in AR-assisted and robotic systems. Existing methods often focus on temporal ordering errors or rely on static prototypes to represent normal actions. However, these approaches typically overlook the common scenario where multiple, distinct actions are valid following a given sequence of executed actions. This leads to two issues: (1) the model cannot effectively detect errors using static prototypes when the inference environment or action execution distribution differs from training;and (2) the model may also use the wrong prototypes to detect errors if the ongoing action label is not the same as the predicted one. To address this problem, we propose an Adaptive Multiple Normal Action Representation (AMNAR) framework. AMNAR predicts all valid next actions and reconstructs their corresponding normal action representations, which are compared against the ongoing action to detect errors. Extensive experiments demonstrate that AMNAR achieves state-of-the-art performance, highlighting the effectiveness of AMNAR and the importance of modeling multiple valid next actions in error detection. The code is available at https://***/iSEElaboratory/AMNAR. Copyright © 2025, The Authors. All rights reserved.

关键词： Error detection

来源：评论

学校读者我要写书评

暂无评论

Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks

arXiv

引用

arXiv 2025年

作者： Zhou, Yu Zheng, Dian Mo, Qijie Lu, Renjie Lin, Kun-Yu Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology China

In this work, we present DEcoupLEd Distillation To Erase (DELETE), a general and strong unlearning method for any class-centric tasks. To derive this, we first propose a theoretical framework to analyze the general form of unlearning loss and decompose it into forgetting and retention terms. Through the theoretical framework, we point out that a class of previous methods could be mainly formulated as a loss that implicitly optimizes the forgetting term while lacking supervision for the retention term, disturbing the distribution of pre-trained model and struggling to adequately preserve knowledge of the remaining classes. To address it, we refine the retention term using "dark knowledge" and propose a mask distillation unlearning method. By applying a mask to separate forgetting logits from retention logits, our approach optimizes both the forgetting and refined retention components simultaneously, retaining knowledge of the remaining classes while ensuring thorough forgetting of the target class. Without access to the remaining data or intervention (i.e., used in some works), we achieve state-of-the-art performance across various benchmarks. What’s more, DELETE is a general solution that can be applied to various downstream tasks, including face recognition, backdoor defense, and semantic segmentation with great performance. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Jiale Zhuo, Shengda He, Jinchun Qiu, Wangjie Zhang, Qinnan Xiong, Zehui Zheng, Zhiming Tang, Yin Chen, Min Wang, Changdong Huang, Shuqiang Jinan University College of Cyber Security Guangzhou China Beihang University Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore Jinan University School of Management Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Computer Guangzhou China Jinan University College of Cyber Security of Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China

The Internet of Things (IoT) collects large volumes of diverse data, with graph data as a critical component, and extensively utilizes Federated Graph Learning (FGL) to process this data while preserving data security. However, the graph data collected by different IoT institutions are relatively independent due to various factors (e.g., data collection methods, geographical locations), and data access is restricted to local environments due to privacy constraints, IoT institutions typically possess heterogeneous feature spaces. Aggregating under these conditions could potentially contaminate local graph representations. Unfortunately, most existing FGL methods tend to overlook this issue. To address this challenge, we propose Federated Graph Learning via Constructing and Sharing Features (FedCSF), a novel FGL framework designed to build a globally consistent feature space and share it among IoT institutions. To construct and extract the feature space, we employ an uniform feature initialization across IoT institutions and design an encoder to extract both global and local feature relationships, thereby facilitating effective collaboration across data from different IoT institutions. Furthermore, we introduce an independent adaptive aggregation strategy to eliminate the integration of harmful knowledge, ensuring that the contributions from each IoT institution are effectively integrated into the global model. We theoretically analyze the convergence of FedCSF. To validate the effectiveness of FedCSF, we conducted extensive experiments under various settings (i.e., cross-datasets, and cross-domains), demonstrating its significant advantages of FedCSF in terms of performance, convergence speed, and practical adaptability © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

HyperSIGMA: Hyperspectral intelligence Comprehension Foundation Model

引用

IEEE Transactions on Pattern Analysis and Machine intelligence 2025年

作者： Wang, Di Hu, Meiqi Jin, Yao Miao, Yuchun Yang, Jiaqi Xu, Yichu Qin, Xiaolei Ma, Jiaqi Sun, Lingyu Li, Chenxing Fu, Chuan Chen, Hongruixuan Han, Chengxi Yokoya, Naoto Zhang, Jing Xu, Minqiang Liu, Lin Zhang, Lefei Wu, Chen Du, Bo Tao, Dacheng Zhang, Liangpei Wuhan University School of Computer Science China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering China Zhongguancun Academy China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing China Sun Yat-sen University School of Geography and Planning China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Chongqing University College of Computer Science China The University of Tokyo Japan RIKEN Center for Advanced Intelligence Project Japan Intelligent Science & Technology Academy Limited CASIC China iFlytek Company Ltd. National Engineering Research Center of Speech and Language Information Processing China Nanyang Technological University College of Computing & Data Science Singapore Henan Academy of Sciences Aerospace Information Research Institute China

Accurate hyperspectral image (HSI) interpretation is critical for providing valuable insights into various earth observation-related applications such as urban planning, precision agriculture, and environmental monitoring. However, existing HSI processing methods are predominantly task-specific and scene-dependent, which severely limits their ability to transfer knowledge across tasks and scenes, thereby reducing the practicality in real-world applications. To address these challenges, we present HyperSIGMA, a vision transformer-based foundation model that unifies HSI interpretation across tasks and scenes, scalable to over one billion parameters. To overcome the spectral and spatial redundancy inherent in HSIs, we introduce a novel sparse sampling attention (SSA) mechanism, which effectively promotes the learning of diverse contextual features and serves as the basic block of HyperSIGMA. HyperSIGMA integrates spatial and spectral features using a specially designed spectral enhancement module. In addition, we construct a large-scale hyperspectral dataset, HyperGlobal-450 K, for pre-training, which contains about 450 K hyperspectral images, significantly surpassing existing datasets in scale. Extensive experiments on various high-level and low-level HSI tasks demonstrate HyperSIGMA's versatility and superior representational capability compared to current state-of-the-art methods. Moreover, HyperSIGMA shows significant advantages in scalability, robustness, cross-modal transferring capability, real-world applicability, and computational efficiency. The code and models will be released at HyperSIGMA. © 1979-2012 IEEE.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Characterization of Exact One-Query Quantum Algorithms for Partial Boolean Functions

引用

Journal of Computer Science & Technology 2023年第6期38卷 1423-1430页

作者：叶泽坤李绿周 Institute of Quantum Computing and Computer Theory School of Computer Science and EngineeringSun Yat-sen UniversityGuangzhou 510006China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen UniversityGuangzhou 510006China

The query model(or black-box model)has attracted much attention from the communities of both classical and quantum ***,quantum advantages are revealed by presenting a quantum algorithm that has a better query complexity than its classical *** the history of quantum algorithms,the Deutsch algorithm and the Deutsch-Jozsa algorithm play a fundamental role and both are exact one-query quantum *** leads us to con-sider the problem:what functions can be computed by exact one-query quantum algorithms?This problem has been ad-dressed in the literature for total Boolean functions and symmetric partial Boolean functions,but is still open for general partial Boolean ***,in this paper,we continue to characterize the computational power of exact one-query quantum algorithms for general partial Boolean ***,we present several necessary and sufficient conditions for a partial Boolean function to be computed by exact one-query quantum ***,inspired by these conditions,we discover some new representative functions that can be computed by exact one-query quantum algorithms but have an essential difference from the already known ***,it is worth pointing out that before our work,the known func-tions that can be computed by exact one-query quantum algorithms are all symmetric functions and the quantum algo-rithm used is essentially the Deutsch-Jozsa algorithm,whereas the functions discovered in this paper are generally asym-metric and new algorithms to compute these functions are ***,this expands the class of functions that can be computed by exact one-query quantum algorithms.

关键词： quantum computing quantum query complexity quantum algorithm

来源：评论

学校读者我要写书评

暂无评论

Meta-Adapter for Self-Supervised Speech Models: A Solution to Low-Resource Speech Recognition Challenges 30

Meta-Adapter for Self-Supervised Speech Models: A Solution t...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Chen, Yaqi Zhang, Hao Yang, Xukui Zhang, Wenlin Qu, Dan School of Information Systems Engineering Information Engineering University China Laboratory for Advanced Computing and Intelligence Engineering China

ISBN: (纸本)9782493814104

Self-supervised models have demonstrated remarkable performance in speech processing by learning latent representations from large amounts of unlabeled data. Although these models yield promising results on low-resource languages, the computational expense of fine-tuning all model parameters is prohibitively high. Adapters offer a solution by incorporating lightweight bottleneck structures into pre-trained models, enabling efficient parameter adaptation for downstream tasks. However, randomly initialized adapters often underperform in low-resource scenarios, limiting their applicability in low-resource languages. To address this issue, we develop the Meta-Adapter for self-supervised models to obtain meta-initialized parameters that facilitate quick adaptation to low-resource languages. Extensive experiments on the Common Voice and FLEURS datasets demonstrate the superior performance of Meta-Adapters on 12 low-resource languages spanning four different language families. Moreover, Meta-adapters show better generalization and extensibility than traditional pretraining methods. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

Imputing DNA Methylation by Transferred Learning Based Neural Network

引用

Journal of Computer Science & Technology 2022年第2期37卷 320-329页

作者： Xin-Feng Wang Xiang Zhou Jia-Hua Rao Zhu-Jin Zhang Yue-Dong Yang School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510000China Key Laboratory of Machine Intelligence and Advanced Computing of Ministry of Education(Sun Yat-sen University)Guangzhou 510000 China

DNA methylation is one important epigenetic type to play a vital role in many diseases including *** the development of the high-throughput sequencing technology,there is much progress to disclose the relations of DNA methylation with ***,the analyses of DNA methylation data are challenging due to the missing values caused by the limitations of current *** many methods have been developed to impute the missing values,these methods are mostly based on the correlations between individual samples,and thus are limited for the abnormal samples in *** this study,we present a novel transfer learning based neural network to impute missing DNA methylation data,namely the TDimpute-DNAmeth *** method learns common relations between DNA methylation from pan-cancer samples,and then fine-tunes the learned relations over each specific cancer type for imputing the missing *** on 16 cancer datasets,our method was shown to outperform other commonly-used *** analyses indicated that DNA methylation is related to cancer survival and thus can be used as a biomarker of cancer prognosis.

关键词： neural network transfer learning DNA methylation data imputation survival analysis

来源：评论

学校读者我要写书评

暂无评论

Design and Validation of a Hyper-converged Blockchain Hardware and Software System Based on Domestic Chips 1st

Design and Validation of a Hyper-converged Blockchain Hardwa...

引用

1st Conference on Blockchain and Web3.0 Technology Innovation and Application, BWTAC 2024

作者： Liu, Xiaolong Yuan, Bo Wu, Faguo Enterprise Technology Center Aerospace Legione Technology Co. Ltd Haidian Beijing100195 China School of Computer Science and Engineering Beihang University Haidian Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Haidian Beijing100191 China Institute of Artificial Intelligence Beihang University Haidian Beijing100191 China Beihang University Haidian Beijing100191 China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Haidian Beijing100191 China

ISBN: (纸本)9789819794119

This paper proposes a hyper-converged blockchain hardware and software sys-tem based on domestic chips. By utilizing domestically firmware, the Linux operating system, X86 architecture Hygon processors, and ARM architecture Phytium processors, combined with servers, storage, network, and independently controllable blockchain technologies, the system achieves integrated hardware and software optimization. This significantly improves performance and scalability. Experimental results demonstrate that the system performs excellently in various high-security application scenarios, providing reliable solutions for government, finance, taxation, transportation, energy, and telecommunications sectors. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

A Review of Intelligent Configuration and Its Security for Complex Networks

引用

Chinese Journal of Electronics 2024年第4期33卷 920-947页

作者： Yue ZHAO Bin YANG Fei TENG Xianhua NIU Ning HU Bo TIAN Science and Technology on Communication Security Laboratory School of Computer and Information Engineering Chuzhou University School of Computing and Artificial Intelligence Southwest Jiaotong University School of Computer and Software Engineering Xihua University Cyberspace Institute of Advanced Technology Guangzhou University

Complex networks are becoming more complex because of the use of many components with diverse technologies. In fact, manual configuration that makes each component interoperable has breed latent danger to system security. There is still no comprehensive review of these studies and prospects for further research. According to the complexity of component configuration and difficulty of security assurance in typical complex networks, this paper systematically reviews the abstract models and formal analysis methods required for intelligent configuration of complex networks, specifically analyzes, and compares the current key technologies such as configuration semantic awareness, automatic generation of security configuration, dynamic deployment, and verification evaluation. These technologies can effectively improve the security of complex networks intelligent configuration and reduce the complexity of operation and maintenance. This paper also summarizes the mainstream construction methods of complex networks configuration and its security test environment and detection index system, which lays a theoretical foundation for the formation of the comprehensive effectiveness verification capability of configuration security. The whole lifecycle management system of configuration security process proposed in this paper provides an important technical reference for reducing the complexity of network operation and maintenance and improving network security.

关键词： Complex networks Intelligent configuration Configuration security Software defined network Lifecycle management

来源：评论

学校读者我要写书评

暂无评论

Enhancing Large-Scale Pre-Trained Models with Mixer for Far-Field ASR 5

Enhancing Large-Scale Pre-Trained Models with Mixer for Far-...

引用

5th International Conference on Artificial intelligence and Computer engineering, ICAICE 2024

作者： Niu, Tong Chen, Yaqi Qu, Dan Hu, Hengbo Information Engineering University Zhengzhou China Laboratory for Advanced Computing and Intelligence Engineering Wuxi China Zhengzhou Xinda Institute of Advanced Technology Zhengzhou China

ISBN: (纸本)9798331528911

Although the significant improvements of Automatic Speech Recognition systems is achieved by the end-to-end modeling technology, especially the use of large-scale pretrained models. Far-Field Speech Recognition still faces the challenges due to signal degradation, such as low signal-to-noise ratio, reverberation, and background noise. To overcome these issues, we introduce an innovative data augmentation technique called Mixer to enhance the performance of large-scale pretrained models in FSR, by interpolated and mixed the features to represent the speech samples and the corresponding losses. Experimental results show that compared to the Whisper acrossed all version, including SpecAugment, the proposed method has reduced 3.6% Word Error Rate. © 2024 IEEE.

关键词： Signal to noise ratio

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：