检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Tianyu Hou, Chengbin Jiang, Rui Zhang, Xuegong Zhou, Chenghu Tang, Ke Lv, Hairong The Ministry of Education Key Laboratory of Bioinformatics Bioinformatics Division Beijing National Research Center for Information Science and Technology Department of Automation Tsinghua University Beijing100084 China The School of Computer Science and Engineering Fuyao Institute of Technology Fuzhou350109 China The State Key Laboratory of Resources and Environmental Information Systems Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China The Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Fuzhou Institute of Data Technology Fuzhou350200 China

Node Importance Estimation (NIE) is a task of inferring importance scores of the nodes in a graph. Due to the availability of richer data and knowledge, recent research interests of NIE have been dedicating to knowledge graphs for predicting future or missing node importance scores. Existing state-of-the-art NIE methods train the model by available labels, and they consider every interested node equally before training. However, the nodes with higher importance often require or receive more attention in real-world scenarios, e.g., people may care more about the movies or webpages with higher importance. To this end, we introduce Label Informed ContrAstive Pretraining (LICAP) to the NIE problem for being better aware of the nodes with high importance scores. Specifically, LICAP is a novel type of contrastive learning framework that aims to fully utilize the continuous labels to generate contrastive samples for pretraining embeddings. Considering the NIE problem, LICAP adopts a novel sampling strategy called top nodes preferred hierarchical sampling to first group all interested nodes into a top bin and a non-top bin based on node importance scores, and then divide the nodes within top bin into several finer bins also based on the scores. The contrastive samples are generated from those bins, and are then used to pretrain node embeddings of knowledge graphs via a newly proposed Predicate-aware Graph Attention Networks (PreGAT), so as to better separate the top nodes from non-top nodes, and distinguish the top nodes within top bin by keeping the relative order among finer bins. Extensive experiments demonstrate that the LICAP pretrained embeddings can further boost the performance of existing NIE methods and achieve the new state-of-the-art performance regarding both regression and ranking metrics. The source code for reproducibility is available at https://***/zhangtia16/LICAP Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Meta-Learning with Task-Adaptive Selection

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Wan, Quan Wang, Maofa Shan, Weifeng Wang, Bin Zhang, Lu Leng, Zhixiong Yan, Bingchen Xu, Yanlin Chen, Huiling Beijing Information Science and Technology University School of Applied Science Beijing100192 China Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software Guilin541004 China Institute of Disaster Prevention School of Emergency Management Langfang065201 China China Geological Survey Command Center of Natural Resources Comprehensive Survey Beijing100055 China Southern University of Science and Technology Department of Earth and Space Sciences Shenzhen518055 China Wenzhou University Department of Computer Science and Artificial Intelligence Wenzhou325035 China

The gradient-based meta-learning algorithm gains meta-learning parameters from a pool of tasks. Starting from the obtained meta-learning parameters, it can achieve better results through fast fine-tuning with only a few gradient descent updates. The two-layer meta-learning approach that shares initialization parameters has achieved good results in solving few-shot learning domain. However, in the training of multiple similar tasks in the inner layer, the difficulty and benefits of the tasks have been consistently overlooked, resulting in conflicts between tasks and ultimately compromising the model to unexpected positions. Therefore, this paper proposes a task-adaptive selection metalearning algorithm called TSML. Specifically, we construct a task selection trainer to assess the difficulty of tasks and calculate their future benefits. Designing more optimal training strategies for each task based on difficulty and benefit, altering the current compromise in multi-task settings, and balancing the impact of tasks on meta-learning parameters. Additionally, the outer meta-parameter updating method for traditional meta-learning has been adjusted, enabling the meta-parameters to attain a better position. By doing so, we can rapidly improve the generalization and convergence of the meta-learning parameters on unknown tasks. Experimental results indicate a 2.1% improvement over the base model in the 4-conv setting, with a more pronounced effect as the neural network is progressively complexified, reaching a 4.1% improvement in resnet12. © 1991-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

TEVA: Training-Efficient and Verifiable Aggregation for Federated Learning for Consumer Electronics in Industry 5.0

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xia, Yuanjun Liu, Yining Chen, Jingxue Liang, Yangfan Khan, Fazlullah Alturki, Ryan Wang, Xiaopei Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software School of Computer and Information Security Guilin541004 China Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou325027 China University of Technology School of Mathematical and Physical Sciences SydneyNSW2007 Australia Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems The Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province The Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing314001 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Zhejiang Ningbo315104 China Umm AI-Qura University Makkah Department of Software Engineering College of Computing Saudi Arabia Riverside Department of Computer Science and Engineering University of California CA92521 United States

Federated learning (FL) has been widely used for privacy-preserving model updates in Industry 5.0, facilitated by 6G networks. Despite FL's privacy-preserving advantages, it remains vulnerable to attacks where adversaries can infer private data from local models or manipulate the central server (CS) to deliver falsified global models. Current privacy-preserving approaches, primarily based on the FedAvg algorithm, fail to optimize training efficiency for non-independent and identically distributed (non-IID) data. This article proposes training-efficient and verifiable aggregation (TEVA) for FL to resolve these issues. This scheme combines threshold Paillier homomorphic encryption (TPHE), verifiable aggregation, and an optimized double momentum update mechanism (OdMum). TEVA not only leverages TPHE to protect the privacy of local models but also ensures the integrity of the global model through a verifiable aggregation mechanism. Additionally, TEVA integrates the OdMum algorithm to effectively address the challenges posed by non-IID data, promoting rapid model convergence and significantly enhancing overall training efficiency. Security analysis indicates that TEVA meets the requirements for privacy protection. Extensive experimental results demonstrate that TEVA can accelerate model convergence while incurring lower computational and communication overheads. © 1975-2011 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Adapter-Enhanced Semantic Prompting for Continual Learning

arXiv

引用

arXiv 2024年

作者： Yin, Baocai Zhao, Ji Jiang, Huajie Hou, Ningning Hu, Yongli Beheshti, Amin Yang, Ming-Hsuan Qi, Yuankai Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Faculty of Information Technology Beijing University of Technology Beijing100124 China Department of Electrical Engineering and Computer Science University of California at Merced MercedCA95343 United States School of Computing Macquarie University SydneyNSW2109 Australia

Continual learning (CL) is essential for enabling models to adapt to dynamic data streams, with the primary challenge being the mitigation of catastrophic forgetting of previously acquired knowledge. Recent advancements have highlighted the potential of prompt-based CL methodologies, which have shown promise in preserving the knowledge embedded within pre-trained models, thereby addressing catastrophic forgetting. However, these methodologies are constrained by their focus on learning visual prompts for individual tasks, resulting in suboptimal generalization to unseen categories. To enhance the model’s ability to retain knowledge from prior tasks while simultaneously improving generalization to new tasks, we introduce a novel, lightweight framework for CL termed Adapter-Enhanced Semantic Prompting (AESP). This framework leverages class semantic information to augment visual features, thereby establishing relational links among different categories. This not only fortifies the retention of prior knowledge but also facilitates adaptation to new tasks. To seamlessly integrate visual and semantic information, we have developed a lightweight Adapter-enhanced Vision Transformer (ViT) architecture specifically designed for feature adaptation. Furthermore, we have implemented a robust Query-key matching strategy to select the optimal task prompt pair, thereby enhancing the accuracy of final predictions. Comprehensive experiments conducted across three benchmark continual learning datasets demonstrate that our proposed framework outperforms several state-of-the-art approaches, showcasing its efficacy and robustness. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

HOIAnimator: Generating Text-Prompt Human-Object Animations Using novel Perceptive Diffusion Models

HOIAnimator: Generating Text-Prompt Human-Object Animations ...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wenfeng Song Xinyu Zhang Shuai Li Yang Gao Aimin Hao Xia Hau Chenglizhao Chen Ning Li Hong Qin Beijing Information Science and Technology University Zhongguancun Laboratory China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Research Unit of Virtual Human and Virtual Surgery (2019RU004) Chinese Academy of Medical Sciences College of Computer Science and Technology China University of Petroleum (East China) Department of Computer Science Stony Brook University (SUNY at Stony Brook) New York USA

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

To date, the quest to rapidly and effectively produce human-object interaction (HOI) animations directly from textual descriptions stands at the forefront of computer vision research. The underlying challenge demands both a discriminating interpretation of language and a comprehen-sive physics-centric model supporting real-world dynamics. To ameliorate, this paper advocates HOIAnimator, a novel and interactive diffusion model with perception ability and also ingeniously crafted to revolutionize the animation of complex interactions from linguistic narratives. The effectiveness of our model is anchored in two ground-breaking innovations: (1) Our Perceptive Diffusion Models (PDM) brings together two types of models: one focused on hu-man movements and the other on objects. This combination allows for animations where humans and objects move in concert with each other, making the overall motion more realistic. Additionally, we propose a Perceptive Message Passing (PMP) mechanism to enhance the communication bridging the two models, ensuring that the animations are smooth and unified; (2) We devise an Interaction Contact Field (ICF), a sophisticated model that implicitly captures the essence of HOls. Beyond mere predictive contact points, the ICF assesses the proximity of human and object to their respective environment, informed by a probabilistic distribution of interactions learned throughout the denoising phase. Our comprehensive evaluation showcases HOlani-mator's superior ability to produce dynamic, context-aware animations that surpass existing benchmarks in text-driven animation synthesis.

关键词： computer vision Technological innovation Message passing Computational modeling Noise reduction Linguistics Animation

来源：评论

学校读者我要写书评

暂无评论

Enabling Communication-Efficient Federated Learning via Distributed Compressed Sensing

Enabling Communication-Efficient Federated Learning via Dist...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yixuan Guan Xuefeng Liu Tao Ren Jianwei Niu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Laboratory for Internet Software Technologies Institute of Software Chinese Academy of Sciences Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

Federated learning (FL) trains a shared global model by periodically aggregating gradients from local devices. Communication overhead becomes a principal bottleneck in FL since participating devices usually suffer from limited bandwidth and unreliable connections in uplink transmission. To address this problem, the gradient compression methods based on compressed sensing (CS) theory have been put forward recently. However, most existing CS-based works compress gradients independently, ignoring the gradient correlations between participants or adjacent communication rounds, which constrains the achievement of higher compression rates. In view of the above observation, we propose a novel gradient compression scheme named FedDCS, guided by distributed compressed sensing (DCS) theory. Following the design philosophy of separate encoding and joint decoding in DCS, FedDCS compresses gradients for participants in each round separately while reconstructing them at the central server jointly via fully exploiting correlated gradients from the previous round, which are known as side information (SI). Benefiting from this design, reconstruction performance is significantly improved with fewer decoding errors also iterations under the identical compression rate, and the total uploading bits to achieve model convergence are considerably reduced. Theoretical analysis and extensive experiments conducted on MNIST and Fashion-MNIST both verify the effectiveness of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Resilience of Power Systems with Fuel Cell-Battery Hybrid Energy Storage System

Enhancing Resilience of Power Systems with Fuel Cell-Battery...

引用

Power science and technology (ICPST), IEEE International Conference on

作者： Mingjian Tuo Muhoza Bertrand Cunzhi Zhao Mulan Zhang Hubei Key Laboratory of Energy Storage and Power Battery Hubei University of Automotive Technology Shiyan China College of Electrical & Information Hubei University of Automotive Technology Shiyan China Department of Engineering and Computer Science McNeese State University Lake Charles Louisiana USA Key Laboratory of Automotive Power Train and Electronics Hubei University of Automotive Technology Shiyan China

ISBN: (数字)9798350349030

ISBN: (纸本)9798350349047

The increasing penetration level of renewable energy resources (RES) has introduced a significant challenge on system frequency dynamics management. Batteries with fast dynamic response are widely used to regulate frequency fluctuation. Considering the degradation of batteries during constant charging and discharging process, it is practical to combine battery with other energy storage to support primary frequency. This paper investigates how hybrid energy storage system including fuel cell (FC) as main and battery as complementary power resources power source can be used to guarantee the frequency stability following the worst contingency while ensuring operational economy. A novel enhanced resilience constrained unit commitment (ER-SCUC) model is proposed to achieve efficient and coordinated utilization of battery energy storage system (BESS) and hydrogen energy storage system (HESS). The economic and low-carbon complementarity between green hydrogen and blue hydrogen are introduced. A case study of a modified IEEE-24 system demonstrates the effectiveness of the proposed ER-SCUC model.

关键词： Fluctuations Power system dynamics Fuel cells Power system stability Green hydrogen Hybrid power systems Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Towards Fair Federated Learning via Unbiased Feature Aggregation

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： He, Zeqing Wang, Zhibo Dong, Xiaowei Sun, Peng Ren, Ju Ren, Kui Zhejiang University State Key Laboratory of Blockchain and Data Security China Institute of Blockchain and Data Security Hangzhou310027 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Zhongguancun Laboratory Beijing100094 China

Federated learning (FL) is a distributed machine learning framework that enables multiple clients to collaboratively train models without raw data exchange. Prior studies on FL mainly focus on optimizing learning performance, enhancing privacy preservation, and improving attack resilience. However, little work studies how to mitigate the unfairness of federated trained models while unfair models would make discriminatory decisions toward certain groups or populations (e.g., favoring males over females), leading to serious ethical concerns. Thus, it is crucial to mitigate model unfairness in FL, yet challenging as this requires centralized access to each data point's fairness-sensitive information (e.g., race, gender), which is prohibited in FL. In this work, we propose a novel fair FL framework FedUFA, where the server can aggregate clients' learned knowledge in an unbiased manner, to obtain fair and high-usability federated trained models. Specifically, to unearth the bias in clients' local data and account for potentially heterogeneous local models, we propose a knowledge distillation-based FL scheme, where clients' knowledge of learned features on a public dataset is amalgamated to the server for aggregation. We train an unbiased feature mapper at the server to remove fairness-sensitive latent features and extract fair representations from clients' submitted raw features. In particular, we design an adversarial training method to train the mapper, which involves a predictor aiming to maximize the prediction accuracy on the FL task and a discriminator intending to help identify fairness-sensitive features. Extensive experiments on real-world datasets demonstrate the effectiveness of FedUFA. © 2025 IEEE. All rights reserved,

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting

arXiv

引用

arXiv 2025年

作者： Liao, Haicheng Kong, Hanlin Wang, Bonan Wang, Chengyue Ye, Wang He, Zhengbing Xu, Chengzhong Li, Zhenning State Key Laboratory of Internet of Things for Smart City University of Macau China Department of Computer and Information Science University of Macau China Senseable City Lab Massachusetts Institute of Technology CambridgeMA United States

Accurate motion forecasting is crucial for safe autonomous driving (AD). This study proposes CoT-Drive, a novel approach that enhances motion forecasting by leveraging large language models (LLMs) and a chain-of-thought (CoT) prompting method. We introduce a teacher-student knowledge distillation strategy to effectively transfer LLMs’ advanced scene understanding capabilities to lightweight language models (LMs), ensuring that CoT-Drive operates in real-time on edge devices while maintaining comprehensive scene understanding and generalization capabilities. By leveraging CoT prompting techniques for LLMs without additional training, CoT-Drive generates semantic annotations that significantly improve the understanding of complex traffic environments, thereby boosting the accuracy and robustness of predictions. Additionally, we present two new scene description datasets, Highway-Text and Urban-Text, designed for fine-tuning lightweight LMs to generate context-specific semantic annotations. Comprehensive evaluations of five real-world datasets demonstrate that CoT-Drive outperforms existing models, highlighting its effectiveness and efficiency in handling complex traffic scenarios. Overall, this study is the first to consider the practical application of LLMs in this field. It pioneers the training and use of a lightweight LLM surrogate for motion forecasting, setting a new benchmark and showcasing the potential of integrating LLMs into AD systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fiel...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jiahe Li Jiawei Zhang Xiao Bai Jin Zheng Xin Ning Jun Zhou Lin Gu State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Jiangxi Research Institute Beihang University Institute of Semiconductors Chinese Academy of Sciences School of Information and Communication Technology Griffith University RIKEN AIP The University of Tokyo

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Radiance fields have demonstrated impressive performance in synthesizing novel views from sparse input views, yet prevailing methods suffer from high training costs and slow inference speed. This paper introduces DNGaussian, a depth-regularized framework based on 3D Gaussian radiance fields, offering real-time and high-quality few-shot novel view synthesis at low costs. Our motivation stems from the highly efficient representation and surprising quality of the recent 3D Gaussian Splatting, despite it will encounter a geometry degradation when input views decrease. In the Gaussian radiance fields, we find this degradation in scene geometry primarily lined to the positioning of Gaussian primitives and can be mitigated by depth constraint. Consequently, we propose a Hard and Soft Depth Regularization to restore accurate scene geometry under coarse monocular depth supervision while maintaining a fine-grained color appearance. To further refine detailed geometry reshaping, we introduce Global-Local Depth Normalization, enhancing the focus on small local depth changes. Extensive experiments on LLFF, DTU, and Blender datasets demonstrate that DNGaussian outperforms state-of-the-art methods, achieving comparable or better results with significantly reduced memory cost, a 25 × reduction in training time, and over 3000 × faster rendering speed. Code is available at: https://***/Fictionarry/DNGaussian.

关键词： Geometry Training Degradation computer vision Three-dimensional displays Costs Color

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：