检索结果-内蒙古大学图书馆

DFMC:Feature-Driven Data-Free Knowledge Distillation

IEEE Transactions on Circuits and systems for Video technology 2025年

作者： Zhang, Zherui Xu, Rongtao Wang, Changwei Xu, Wenhao Chen, Shunpeng Xu, Shibiao Xu, Guangyuan Guo, Li Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing100876 China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China Qilu University of Technology Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250316 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China

Data-Free Knowledge Distillation (DFKD) enables knowledge transfer from teacher networks without access to the real dataset. However, generator-based DFKD methods often suffer from insufficient diversity or low-confidence in synthetic images, negatively impacting student network performance. This paper introduces DFMC, a generative feature-driven framework to mitigate the inherent limitations of DFKD. We propose exploiting semantic description between generative feature domains to guide augmentation strategies, avoiding random abstract inputs caused by inconsistent semantic quality. Then, by applying noise to the generative features, we produce contrastive learning pairs indirectly, limiting the sampling range of the feature domain to encourage the student network to learn domain-invariant features. Finally, we guide the student network to deeply mimic the teacher’s layer-wise implicit classification behavior for the augmented synthetic images. Extensive experiments across various datasets and downstream tasks demonstrate the effectiveness of DFMC, achieving significant improvements while preventing student networks from overfitting to semantic ambiguous images. © 1991-2012 IEEE.

关键词： Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Integrated Beamforming and Resource Allocation in RIS-Assisted mmWave Networks based on Deep Reinforcement Learning

Integrated Beamforming and Resource Allocation in RIS-Assist...

引用

Annual IEEE Northeast Workshop on Circuits and systems (NEWCAS)

作者： Di Chen Hui Gao Na Chen Ruohan Cao Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Graduate School of Science and Technology Nara Institute of Science and Technology Ikoma Japan

Reconfigurable intelligent surface (RIS) has gained wide attention recently as a promising solution to address the blockage issue in millimeter wave (mmWave) communication networks. In this paper, we consider a RIS-assisted mmWave communication system consisting of multiple RISs and users. A novel integrated scheme based on deep reinforcement learning (DRL) is proposed to jointly optimize the hybrid beamforming, phase shifts, and power allocation. Specifically, we design a multi-variable action output to achieve integrated optimization in both beam and power domains. We also design a weighted sum reward to balance the influence of beam and power domain optimizing variables in the training process. Experimental results demonstrate that the proposed DRL-based method can achieve at least 37% higher sum rates than the baseline algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Time-Constrained Path Recommendation with User’s Preference

Dynamic Time-Constrained Path Recommendation with User’s Pr...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Yixi Wu Yaying Zhang Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9781665442084

Path recommendation is an essential application in people’s daily life. However, drivers’ experience hidden in their driving history and their personal preferences are less considered in path planning. In this paper we propose a dynamic time-constrained path recommendation method, utilizing the historical GPS trajectory information and user preferences. First, based on graph entropy, critical intersections are extracted from trajectory information to simplify the road network structure. Then the time-dependent mostly chosen path (TDMCP) is obtained by trajectories processing to determine the time-varying paths between critical intersections. Thus the original complex road network is abstracted as a search subnet. Finally we propose an improved dynamic A* search (IDAS) on the search sub-net to find the candidate paths satisfying the time-constraints, and further allow users to set personal preferences to select the final optimal path. The proposed method is validated on the real-world data set, and the result shows that the proposed method surpasses the competing ones especially on long distance path recommendation.

关键词： Roads Conferences Entropy Trajectory History Data mining Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Feedback-based Coarse Time-Granularity POI Recommendation and Itinerary Planning

Feedback-based Coarse Time-Granularity POI Recommendation an...

引用

Chinese Automation Congress (CAC)

作者： Jie Zong Zhijun Ding The Key Laboratory of Embedded System and Service Computing Ministry of Education TONGJI University Shanghai China

ISBN: (纸本)9781665426480

For tourists, planning their own travel itinerary to a strange city is really challenging. Although there are many researches on Point of Interests (POIs) recommendation and itinerary planning, two problems occur in currently proposed recommendation algorithms. First, the time granularity of the algorithms is too fine. POI recommendation should be considered within a more coarse-grained time factor. For example, a visitor wouldn’t like to visit a water park in winter, although he appears to love such places. However, seldom researches have taken this into consideration. Second, most of the algorithms build their models based on the tourists’ trajectory, which means, they did not consider users’ feedback. In fact, quite a number of tourists do not like their travel experience and give negative feedbacks after their visits. In this situation, we shouldn’t recommend similar POIs to this user because he may not like such kind of scenic spots at all. To address these two problems, this paper proposes an algorithm called Feedback-based Coarse Time-Granularity POI Recommendation, which can extract information from comments and distinguish tourists’ attitudes towards the POIs they have visited. At the same time, the coarse-grained time factor is considered while making recommendations. In addition, an itinerary planning algorithm is proposed. Experiments show that our algorithm can reach SOTA.

关键词： Negative feedback Automation Urban areas Planning Trajectory Time factors Data mining

来源：评论

学校读者我要写书评

暂无评论

NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points

arXiv

引用

arXiv 2025年

作者： Zhang, Qianyi Luo, Wentao Liu, Boyi Zhang, Ziyang Wang, Yaoyuan Liu, Jingtai Institute of Robotics and Automatic Information System Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin China Advanced Computing and Storage Lab Huawei 2012 Lab China Department of Electronic and Computer Engineering The Kong Kong University of Science and Technology Hong Kong

Motion planning in navigation systems is highly susceptible to upstream perceptual errors, particularly in human detection and tracking. To mitigate this issue, the concept of guidance points—a novel directional cue within a reinforcement learning-based framework—is introduced. A structured method for identifying guidance points is developed, consisting of obstacle boundary extraction, potential guidance point detection, and redundancy elimination. To integrate guidance points into the navigation pipeline, a perception-to-planning mapping strategy is proposed, unifying guidance points with other perceptual inputs and enabling the RL agent to effectively leverage the complementary relationships among raw laser data, human detection and tracking, and guidance points. Qualitative and quantitative simulations demonstrate that the proposed approach achieves the highest success rate and near-optimal travel times, greatly improving both safety and efficiency. Furthermore, real-world experiments in dynamic corridors and lobbies validate the robot’s ability to confidently navigate around obstacles and robustly avoid pedestrians. © 2025, CC BY.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

MacLight: Multi-scene Aggregation Convolutional Learning for Traffic Signal Control 25

MacLight: Multi-scene Aggregation Convolutional Learning for...

引用

Proceedings of the 24th International Conference on Autonomous Agents and Multiagent systems

作者： Sunbowen Lee Hongqin Lyu Yicheng Gong Yingying Sun Chao Deng College of Science Hubei Province Key Laboratory of System Science in Metallurgical Process Wuhan University of Science and Technology Wuhan China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences & University of Chinese Academy of Sciences Beijing China College of Science Wuhan University of Science and Technology Wuhan China School of Automobile and Traffic Engineering Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9798400714269

Reinforcement learning methods have proposed promising traffic signal control policy that can be trained on large road networks. Current SOTA methods model road networks as topological graph structures, incorporate graph attention into deep Q-learning, and merge local and global embeddings to improve policy. However, graph-based methods are difficult to parallelize, resulting in huge time overhead. Moreover, none of the current peer studies have deployed dynamic traffic systems for experiments, which is far from the actual *** this context, we propose Multi-Scene Aggregation Convolutional Learning for traffic signal control (MacLight), which offers faster training speeds and more stable performance. Our approach consists of two main components. The first is the global representation, where we utilize variational autoencoders to compactly compress and extract the global representation. The second component employs the proximal policy optimization algorithm as the backbone, allowing value evaluation to consider both local features and global embedding representations. This backbone model significantly reduces time overhead and ensures stability in policy updates. We validated our method across multiple traffic scenarios under both static and dynamic traffic systems. Experimental results demonstrate that, compared to general and domian SOTA methods, our approach achieves superior stability, optimized convergence levels and the highest time efficiency. The code is under https://***/Aegis1863/MacLight.

关键词： multi-agent reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

SLMP: A Scientific Literature Management Platform Based on Large Language Models

SLMP: A Scientific Literature Management Platform Based on L...

引用

IEEE International Conference on Big Knowledge (ICBK)

作者： Menghao Guo Jinling Jiang Fan Wu Shanxin Sun Chen Zhang Wenhui Li Zeyi Sun Guangyong Chen Xindong Wu Research Center for Life Sciences Computing Zhejiang Lab Hangzhou China Research Center for Data Hub and Security Zhejiang Lab Hangzhou China Research Center for High Efficiency Computing System Zhejiang Lab Hangzhou China Key Laboratory of Knowledge Engineering With Big Data Hefei University of Technology Hefei China

ISBN: (数字)9798331508821

ISBN: (纸本)9798331508838

This paper presents a Scientific Literature Management Platform (SLMP, demo link 1 ) based on large language models (LLMs). The platform consists of four modules: literature management, literature extraction, literature retrieval, and question answering. The core techniques used to support the four modules across the platform include a fine-tuned model PaperExtractGPT and a continual pre-training model ChatPaperGPT based on ChatGLM 2 using the data from scientific research literature, responsible for information extraction and communication, respectively. Due to their powerful capabilities in natural language understanding and generation, LLMs can understand complex scientific concepts based on the provided contexts, and thus generate high-quality texts and conduct in-depth information retrieval and question answering. Our platform can help researchers manage and utilize literature more effectively and efficiently for finding relevant literature, obtaining required information, and generating new knowledge.

关键词： Training Large language models Knowledge graphs Information retrieval Data models Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

Dynamic detection technology of encryption algorithm based on Pin

Dynamic detection technology of encryption algorithm based o...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Junpeng Qu Gaolei Du Yunge Sun Yong Fu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Quan Cheng Laboratory Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Aiming at the problem that malicious software uses encryption algorithm to hide its own malicious code and avoid detection, a dynamic detection technology based on Pin encryption algorithm is proposed. Use Pin to get the instruction flow of executable file running, then identify the function call in the instruction flow to get the function call framework, find the loop body in the calling function, and then carry out the encryption algorithm instruction detection and encryption algorithm constant detection on the loop body. If the detection passes, it can be considered that a component of the encryption algorithm is found. Then the complete encryption algorithm is found according to the generated function call framework. Experiments show that this method can effectively identify the encryption algorithms hidden in executable files.

关键词： Heuristic algorithms Software algorithms Cyberspace Data science Feature extraction Malware Encryption Pins

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

arXiv

引用

arXiv 2023年

作者： Zhang, Yechao Hu, Shengshan Zhang, Leo Yu Shi, Junyu Li, Minghui Liu, Xiaogeng Wan, Wei Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Adversarial examples for deep neural networks (DNNs) have been shown to be transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical use. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient similarity. Building on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifest in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other,

关键词： Deep neural networks

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：