检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Pre-Encoding Representation and Sturcture Embedding for Efficient and Low-Resource Knowledge Graph Completion

Joint Pre-Encoding Representation and Sturcture Embedding fo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Qiu, Chenyu Qian, Pengjiang Wang, Chuang Yao, Jian Liu, Li Fang, Wei Ng, Eddie-Yin-Kwee School of Artificial Intelligence and Computer Science Jiangnan University China Engineering Research Center of Intelligent Technology for Healthcare Ministry of Education Jiangnan University China Big Data Center Affiliated Hospital of Jiangnan University China Nanyang Technological University Singapore

ISBN: (纸本)9798891761643

Knowledge graph completion (KGC) aims to infer missing or incomplete parts in knowledge graph. The existing models are generally divided into structure-based and description-based models, among description-based models often require longer training and inference times as well as increased memory usage. In this paper, we propose Pre-Encoded Masked Language Model (PEMLM) to efficiently solve KGC problem. By encoding textual descriptions into semantic representations before training, the necessary resources are significantly reduced. Furthermore, we introduce a straightforward but effective fusion framework to integrate structural embedding with pre-encoded semantic description, which enhances the model's prediction performance on 1-N relations. The experimental results demonstrate that our proposed strategy attains state-of-the-art performance on the WN18RR (MRR+5.4% and Hits@1+6.4%) and UMLS datasets. Compared to existing models, we have increased inference speed by 30x and reduced training memory by approximately 60%. © 2024 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Pseudocapacitive Heteroatom-Doped Carbon Cathode for Aluminum-Ion Batteries with Ultrahigh Reversible Stability

引用

Energy & Environmental Materials 2024年第5期7卷 150-159页

作者： Jiahui Li Jehad KEl-Demellawi Guan Sheng Jonas Björk Fanshuai Zeng Jie Zhou Xiaxia Liao Junwei Wu Johanna Rosen Xingjun Liu Husam N.Alshareef Shaobo Tu School of Physics and Materials Science Nanchang University999 Xuefu RoadHonggutan DistrictNanchang 330031China School of Materials Science and Engineering and Institute of Materials Genome and Big DataHarbin Institute of TechnologyShenzhen 518055China KAUST Upstream Research Center(KURC) EXPEC-ARCSaudi AramcoThuwal 23955Saudi Arabia Materials Design Division Department of PhysicsChemistry and Biology(IFM)Linköping UniversitySE-58183LinköpingSweden Physical Science and Engineering(PSE)Division King Abdullah University of Science and TechnologyThuwal 23955Saudi Arabia

Aluminum(Al)-ion batteries have emerged as a potential alternative to conventional ion batteries that rely on less abundant and costly materials like ***,given the nascent stage of advancement in Al-ion batteries(AIBs),attaining electrode materials that can leverage both intercalation capacity and structural stability remains ***,we demonstrate a C3N4-derived layered N,S heteroatom-doped carbon,obtained at different pyrolysis temperatures,as a cathode material for AIBs,encompassing the diffusion-controlled intercalation and surface-induced capacity with ultrahigh *** developed layered N,S-doped corbon(N,S-C)cathode,synthesized at 900℃,delivers a specific capacity of 330 mAhg^(-1)with a relatively high coulombic efficiency of~85%after 500 cycles under a current density of 0.5 A g^(-1).Owing to its reinforced adsorption capability and enlarged interlayer spacing by doping N and S heteroatoms,the N,S-C900 cathode demonstrates outstanding energy storage capacity with excellent rate performance(61 mAhg^(-1)at 20 A g^(-1))and ultrahigh reversibility(90 mAhg^(-1)at 5Ag^(-1)after 10000cycles).

关键词： 2D carbon adsorption energy heteroatoms-doping high capacity long cycling life

来源：评论

学校读者我要写书评

暂无评论

Causal fMRI-Mamba: Causal State Space Model for Neural Decoding and Brain Task States Recognition

Causal fMRI-Mamba: Causal State Space Model for Neural Decod...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Deng, Weihao Han, Fei Ling, Qinghua Liu, Qing Han, Henry School of Computer Science and Communication Engineering JiangSu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China School of Computer Jiangsu University of Science and Technology China School of Electronic and Information Engineering West Anhui University China School of Engineering and Computer Science Baylor University United States

ISBN: (纸本)9798350368741

Deep learning advances neural decoding in functional magnetic resonance imaging (fMRI) tasks with convolution and attention-based methods. However, these methods struggle with capturing global spatiotemporal information due to high dimensionality, noise and inter-individual difference of fMRI, which also increase computational complexity and prior bias. To this end, a novel causal state space model, Causal fMRI-Mamba, is proposed for neural decoding and task state mapping. It effectively captures global spatiotemporal information via eliminating local redundancies and capturing long-distance dependencies. Meanwhile, a causal representation framework is designed to extract invariant high-order features and disentangle related causal features, enhancing model performance. Furthermore, a dense connection module is expanded to prevent significant causal information loss in hidden states of inter layers. On the HCP brain task state classification task, Causal fMRI-Mamba achieves better performance and generalization than comparison methods. © 2025 IEEE.

关键词： causal representation learning Neuro-decoding state space model task-based fMRI

来源：评论

学校读者我要写书评

暂无评论

The Caching and Pricing Strategy for Information-Centric Networking with Advertisers’Participation

引用

China Communications 2024年第3期21卷 283-295页

作者： Zheng Quan Yan Wenliang Wu Rong Tan Xiaobin Yang Jian Yuan Liu Xu Zhenghuan Laboratory for Future Networks Department of AutomationUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China Suzhou Nuclear Power Research Institute Suzhou 215004China National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data(NEL-PSRPC) China Academy of Electronics and Information Technology of CETCBeijing 100041China

As users’access to the network has evolved into the acquisition of mass contents instead of IP addresses,the IP network architecture based on end-to-end communication cannot meet users’***,the Information-Centric Networking(ICN)came into *** a technical point of view,ICN is a promising future network *** and customizing a reasonable pricing mechanism plays a positive role in promoting the deployment of *** current research on ICN pricing mechanism is focused on paid ***,we study an ICN pricing model for free content,which uses game theory based on Nash equilibrium to *** this work,advertisers are considered,and an advertiser model is established to describe the economic interaction between advertisers and ICN *** solution can formulate the best pricing strategy for all ICN entities and maximize the benefits of each *** extensive analysis and numerical results show that the proposed pricing framework is significantly better than existing solutions when it comes to free content.

关键词： advertisers cache free content Information-Centric Networking pricing strategy

来源：评论

学校读者我要写书评

暂无评论

SymILO: a symmetry-aware learning framework for integer linear optimization 24

SymILO: a symmetry-aware learning framework for integer line...

引用

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

作者： Qian Chen Tianjian Zhang Linxin Yang Qingyu Han Akang Wang Ruoyu Sun Xiaodong Luo Tsung-Hui Chang School of Science and Engineering The Chinese University of Hong Kong Shenzhen China and Shenzhen Research Institute of Big Data China Shenzhen Research Institute of Big Data China and School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China School of Data Science The Chinese University of Hong Kong Shenzhen China and Shenzhen International Center For Industrial And Applied Mathematics Shenzhen Research Institute of Big Data China

ISBN: (纸本)9798331314385

Integer linear programs (ILPs) are commonly employed to model diverse practical problems such as scheduling and planning. Recently, machine learning techniques have been utilized to solve ILPs. A straightforward idea is to train a model via supervised learning, with an ILP as the input and an optimal solution as the label. An ILP is symmetric if its variables can be permuted without changing the problem structure, resulting in numerous equivalent and optimal solutions. Randomly selecting an optimal solution as the label can introduce variability in the training data, which may hinder the model from learning stable patterns. In this work, we incorporate the intrinsic symmetry of ILPs and propose a novel training framework called SymILO. Specifically, we modify the learning task by introducing solution permutation along with neural network weights as learnable parameters and then design an alternating algorithm to jointly optimize the loss function. We conduct extensive experiments on ILPs involving different symmetries and the computational results demonstrate that our symmetry-aware approach significantly outperforms three existing methods—achieving 50.3%, 66.5%, and 45.4% average improvements, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tensor and Minimum Connected Dominating Set based Confident Information Coverage Reliability Evaluation for IoT

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2024年第03期10卷 547-561页

作者： Xiao, Ziheng Zhu, Chenlu Feng, Wei Liu, Shenghao Deng, Xianjun Lu, Hongwei Yang, Laurence T. Park, Jong Hyuk Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430074 China Artificial Intelligence and Intelligent Transportation Joint Technical Center of HUST and Hubei Chutian Intelligent Transportation Company Ltd United States Network and Industrial Control Information Security Technology Department China Nuclear Power Operation Technology Company Ltd. 1011 Xiongchu Avenue Hubei Wuhan430070 China The Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of

Internet of Things (IoT) reliability evaluation contributes to the sustainable computing and enhanced stability of the network. Previous algorithms usually evaluate the reliability of IoT by enumenating the states of nodes and networks, which are difficult to handle IoT with hundreds of nodes because the computational cost. In this paper, a novel algorithm, TMCRA, is proposed to evaluate the reliability of IoT in complex network environment, which consider both coverage and connectivity. For coverage, TMCRA employs the Confident Information Coverage (CIC) model to divide the target area into independent grids and calculates the coverage rate. In terms of connectivity, TMCRA forming the Virtual Backbone Network (VBN) based on two proposed methods: TMA and MGIN, and evaluate connectivity by analyzing the VBN rather than the whole network. The TMA and MGIN are two algorithms for constructing Minimum Connected Dominant Sets (MCDS), which are suitable for different scale networks. Finally, based on the data of coverage and connectivity, TMCRA utilizes tensors for the unified modeling and representation of network structure, and calculates IoT reliability based on the tensors. Simulations are carried out for various sizes of IoT to show the advantages and effectiveness of the proposed approach in reliability evaluation. © 2016 IEEE.

关键词： data reliability

来源：评论

学校读者我要写书评

暂无评论

Accelerating Parallel Sampling of Diffusion Models 41

Accelerating Parallel Sampling of Diffusion Models

引用

41st International Conference on Machine Learning, ICML 2024

作者： Tang, Zhiwei Tang, Jiasheng Luo, Hao Wang, Fan Chang, Tsung-Hui School of Science and Engineering The Chinese University of Hong Kong Shenzhen China DAMO Academy Alibaba Group China Hupan Lab Zhejiang Province China Shenzhen Research Institute of Big Data Shenzhen China

Diffusion models have emerged as state-of-the-art generative models for image generation. However, sampling from diffusion models is usually time-consuming due to the inherent autoregressive nature of their sampling process. In this work, we propose a novel approach that accelerates the sampling of diffusion models by parallelizing the autoregressive process. Specifically, we reformulate the sampling process as solving a system of triangular nonlinear equations through fixed-point iteration. With this innovative formulation, we explore several systematic techniques to further reduce the iteration steps required by the solving process. Applying these techniques, we introduce ParaTAA, a universal and training-free parallel sampling algorithm that can leverage extra computational and memory resources to increase the sampling speed. Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms such as DDIM and DDPM by a factor of 4∼14 times. Notably, when applying ParaTAA with 100 steps DDIM for Stable Diffusion, a widely-used text-to-image diffusion model, it can produce the same images as the sequential sampling in only 7 inference steps. The code is available at https://***/TZW1998/ParaTAA-Diffusion. Copyright 2024 by the author(s)

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV Systems

引用

IEEE Transactions on Mobile Computing 2025年第07期24卷 6315-6332页

作者： Chen, Zheyi Huang, Sijin Min, Geyong Ning, Zhaolong Li, Jie Zhang, Yan Fuzhou University College of Computer and Data Science Fuzhou350116 China Ministry of Education Engineering Research Center of Big Data Intelligence Fuzhou350002 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China University of Exeter Department of Computer Science Faculty of Environment Science and Economy ExeterEX4 4QF United Kingdom Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China University of Oslo Department of Informatics Oslo0316 Norway

Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on prior knowledge and rarely consider efficient resource allocation during the service migration process, making it hard to reach optimal performance in dynamic IoV environments. To address these important challenges, we propose SR-CL, a novel mobility-aware seamless Service migration and Resource allocation framework via Convex-optimization-enabled deep reinforcement Learning in multi-edge IoV systems. First, we decouple the Mixed Integer Nonlinear Programming (MINLP) problem of service migration and resource allocation into two sub-problems. Next, we design a new actor-critic-based asynchronous-update deep reinforcement learning method to handle service migration, where the delayed-update actor makes migration decisions and the one-step-update critic evaluates the decisions to guide the policy update. Notably, we theoretically derive the optimal resource allocation with convex optimization for each MEC server, thereby further improving system performance. Using the real-world datasets of vehicle trajectories and testbed, extensive experiments are conducted to verify the effectiveness of the proposed SR-CL. Compared to benchmark methods, the SR-CL achieves superior convergence and delay performance under various scenarios. © 2025 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Federated Learning in Fragmented Digital Healthcare Systems: A Visionary Perspective 15

Unleashing the Power of Federated Learning in Fragmented Dig...

引用

15th International Conference on Software, Knowledge, Information Management and Applications, SKIMA 2023

作者： Tania, Marzia Hoque Clifton, David A. University of New South Wales Centre for Big Data Research in Health Sydney Australia Institute of Biomedical Engineering University of Oxford Department of Engineering Science Oxford United Kingdom Suzhou China

ISBN: (纸本)9798350316551

Digital healthcare landscape, including infrastructure, governance, interoperability, and user adoption, are continuously evolving, some taking more centralised approach, while others with higher degree of fragmentation. Attitude towards centralised healthcare systems in affluent countries are primarily influenced by historical development, infrastructure investments, and regulatory frameworks, which offers advantages with respect to standardised practises, centralised decision making, and economies of scale. In contrast, complexities due to diverse stakeholders, interoperability challenges, privacy and security concerns often pose challenges in achieving a completely centralised healthcare system even in high income countries such as the United Kingdom or in federal systems such as the United States. Moreover, decentralised healthcare systems are more prevalent in resource-poor countries. This paper presents our viewpoint and perspectives on the potential of federated learning in decentralised healthcare systems, especially in countries with infrastructure constraints and discusses its advantages, privacy and security concerns, and challenges. As data-hungry artificial intelligence-enabled systems are gradually changing the healthcare ecosystem, federated learning presents an opportunity for distributing the machine learning training process across multiple decentralised edge devices with reduced data transfer. Therefore, the decentralised digital healthcare system can leverage the collaborative model training while protecting highly sensitive and personal health information. However, challenges related to data heterogeneity, communication latency, and model aggregation need to be addressed for successful implementation of such systems. Adapting the federated learning framework to the specific needs and constraints of low and middle-income countries is crucial to unlock its potential in improving healthcare outcomes. © 2023 IEEE.

关键词： data transfer

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：