检索结果-内蒙古大学图书馆

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

FEAT: Towards Fast Environment-Adaptive Task Offloading and Power Allocation in MEC

FEAT: Towards Fast Environment-Adaptive Task Offloading and ...

引用

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

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

Mobile edge computing (MEC) has been proposed to provide mobile devices with both satisfactory computing resources and latency. key issues in MEC include task offloading and power allocation (TOPA), for which deep reinforcement learning (DRL) is becoming a popular methodology. However, most DRL-based TOPA approaches are typically developed in a certain environment, lacking the adaptability to unseen environments. Motivated by this, this paper proposes a Fast Environment-Adaptive TOPA (FEAT) approach that could adapt to unseen environments with little fine-tuning. Specifically, we first split MEC states into the internal state and environmental state. Then, based on these two types of states, we develop two main components of FEAT — a group of internal state-dependent TOPA meta-policies and an environmental state-embedded steerer. Meta-policies learn TOPA skills within the internal state space (allowing reusing meta-policies in different environments), while the steerer learns to choose appropriate meta-policies according to embedded environmental states. When encountering an unseen environment with the same internal state space, FEAT only needs to fine-tune the steerer using the newly embedded environmental state with few internal state explorations. Extensive experimental results on simulation and testbed demonstrate that FEAT outperforms the state-of-the-art by more than 16.4% in terms of fine-tuning speeds.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models

arXiv

引用

arXiv 2023年

作者： Zhao, Mengyi Liu, Mengyuan Ren, Bin Dai, Shuling Sebe, Nicu The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The School of Intelligent Systems Engineering Sun Yatsen University Shenzhen510275 China Guangdong Provincial Key Laboratory of Fire Science and Technology Guanzhou510006 China University of Pisa University of Trento Italy Jiangxi Research Institute Beihang University China University of Trento Trento Italy

Diffusion-based generative models have recently emerged as powerful solutions for high-quality synthesis in multiple domains. Leveraging the bidirectional Markov chains, diffusion probabilistic models generate samples by inferring the reversed Markov chain based on the learned distribution mapping at the forward diffusion process. In this work, we propose Modiff, a conditional paradigm that benefits from the denoising diffusion probabilistic model (DDPM) to tackle the problem of realistic and diverse action-conditioned 3D skeleton-based motion generation. We are a pioneering attempt that uses DDPM to synthesize a variable number of motion sequences conditioned on a categorical action. We evaluate our approach on the large-scale NTU RGB+D dataset and show improvements over state-of-the-art motion generation methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Layout-Bridging Text-to-Image Synthesis

arXiv

引用

arXiv 2022年

作者： Liang, Jiadong Pei, Wenjie Lu, Feng The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Department of Computer Science Harbin Institute of Technology at Shenzhen Shenzhen518057 China

The crux of text-to-image synthesis stems from the difficulty of preserving the cross-modality semantic consistency between the input text and the synthesized image. Typical methods, which seek to model the text-to-image mapping directly, could only capture keywords in the text that indicates common objects or actions but fail to learn their spatial distribution patterns. An effective way to circumvent this limitation is to generate an image layout as guidance, which is attempted by a few methods. Nevertheless, these methods fail to generate practically effective layouts due to the diversity of input text and object location. In this paper we push for effective modeling in both text-to-layout generation and layout-to-image synthesis. Specifically, we formulate the text-to-layout generation as a sequence-to-sequence modeling task, and build our model upon Transformer to learn the spatial relationships between objects by modeling the sequential dependencies between them. In the stage of layout-to-image synthesis, we focus on learning the textual-visual semantic alignment per object in the layout to precisely incorporate the input text into the layout-to-image synthesizing process. To evaluate the quality of generated layout, we design a new metric specifically, dubbed Layout Quality Score, which considers both the absolute distribution errors of bounding boxes in the layout and the mutual spatial relationships between them. Extensive experiments on three datasets demonstrate the superior performance of our method over state-of-the-art methods on both predicting the layout and synthesizing the image from the given text. © 2022, CC BY.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Fast Robot Hierarchical Exploration Based on Deep Reinforcement Learning

Fast Robot Hierarchical Exploration Based on Deep Reinforcem...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Shun Zuo Jianwei Niu Lu Ren Zhenchao Ouyang State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University Beijing China Beihang Hangzhou Innovation Institute Yuhang Beihang University Beijing China

This paper investigates the use of reinforcement learning for autonomous exploration in an unknown environment. Autonomous exploration is crucial in many situations, such as urban search, security inspection, environmental mapping, etc. Traditional approaches focused on frontiers are unlikely to span a variety of enormously complex scenarios. Convergence is a little more difficult for learning-based approaches, which can adapt to many different environments. Consequently, a hierarchical exploration framework is built using frontier information. We propose a reinforcement learning-based local decision exploration model that uses deep neural networks to learn the optimal strategy from the environment. To prevent falling into local optimization, we also suggest a global rescue module to assist the robot in returning to the proper exploration track. Compared with other hierarchical methods, the framework is more effective and resilient in many contexts, greatly decreasing the total completion time and path length.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task Assignment of Unmanned Platform Cluster Considering Special state

Task Assignment of Unmanned Platform Cluster Considering Spe...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Jiacheng Jiang Jin Xiao Xiaoguang Hu Lei Liu Fei Long State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Beijing Electromechanical Institute Beijing China State Grid Jibei Electric Power Co. Ltd Beijing China

ISBN: (纸本)9781665409858

This paper addresses the task assignment problem of unmanned platform with the special states, where the special state can be parts damage, insufficient power, insufficient ammunition, etc. To be specific, when the unmanned platform is in the special state mentioned above, it needs to give up the original mission target and then return to the designated position for supply. After reaching the designated spot and completing the supply, previous mission target can be executed again. We propose an algorithm framework that combines A * algorithm and discrete particle swarm optimization algorithm, where A * algorithm is used to deal with the path planning problem, which get the paths as well as the distances, and discrete particle swarm optimization algorithm is used to deal with the task assignment problem to realize the task assignment of unmanned platform cluster considering the special state. Illustrative examples demonstrate the effectiveness of the proposed framework.

关键词： Industrial electronics Simulation Clustering algorithms Path planning Task analysis Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration

Bold but Cautious: Unlocking the Potential of Personalized F...

引用

International Conference on Computer Vision (ICCV)

作者： Xinghao Wu Xuefeng Liu Jianwei Niu Guogang Zhu Shaojie Tang State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China Jindal School of Management University of Texas at Dallas USA

Personalized federated learning (PFL) reduces the impact of non-independent and identically distributed (non-IID) data among clients by allowing each client to train a personalized model when collaborating with others. A key question in PFL is to decide which parameters of a client should be localized or shared with others. In current mainstream approaches, all layers that are sensitive to non-IID data (such as classifier layers) are generally personalized. The reasoning behind this approach is understandable, as localizing parameters that are easily influenced by non-IID data can prevent the potential negative effect of collaboration. However, we believe that this approach is too conservative for collaboration. For example, for a certain client, even if its parameters are easily influenced by non-IID data, it can still benefit by sharing these parameters with clients having similar data distribution. This observation emphasizes the importance of considering not only the sensitivity to non-IID data but also the similarity of data distribution when determining which parameters should be localized in PFL. This paper introduces a novel guideline for client collaboration in PFL. Unlike existing approaches that prohibit all collaboration of sensitive parameters, our guideline allows clients to share more parameters with others, leading to improved model performance. Additionally, we propose a new PFL method named FedCAC, which employs a quantitative metric to evaluate each parameter’s sensitivity to non-IID data and carefully selects collaborators based on this evaluation. Experimental results demonstrate that FedCAC enables clients to share more parameters with others, resulting in superior performance compared to state-of-the-art methods, particularly in scenarios where clients have diverse distributions. The code is integrated into our FL training framework: https://***/kxzxvbk/Fling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Double-Blinded Finder: A Two-Side Privacy-Preserving Approach for Finding Missing Children 3rd

Double-Blinded Finder: A Two-Side Privacy-Preserving Approac...

引用

3rd EAI International Conference on Robotic Sensor Networks, ROSENET 2019

作者： Jin, Xin Ge, Shiming Song, Chenggen Li, Xiaodong Lei, Jicheng Wu, Chuanqiang Yu, Haoyang Beijing Electronic Science and Technology Institute Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China OracleChain Technology Beijing China CETC Big Data Research Institute Co. Ltd. Guizhou China

ISBN: (纸本)9783030460310

Posting photos of suspected missing children on the street and posting them to social networks can help find missing children, but posting them to the Internet without protection may create privacy issues. In order to solve this problem, we propose Double-Blinded Finder, which is mainly used for low-dimensional multi-attribute matching of children’s face and blind face to find missing children and has high efficiency. To obtain enough knowledge for representing child faces, we build the Labeled Child Face in the Wild dataset, which contains 60K Internet images with 6K unique identities. We use this dataset to train a multitasking deep learning facial model, using a 128-dimensional feature vector and age and gender attributes to describe the child’s face. Due to the use of the face descriptor generation key, facial photos from the social network and facial information from the parents of the missing child are encrypted. In addition, we devise inner-production encryption to run blind face matching in the public cloud. In this manner, Double-Blinded Finder can provide efficient face matching while protecting the privacies of both sides: 1) Suspicious missing children in order to avoid human rights violations, 2) The real missing child is to retain the second victim. Experiments show that our system can achieve the actual performance of children’s face matching, and privacy leakage is negligible. © 2021, Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

SVDFed: Enabling Communication-Efficient Federated Learning via Singular-Value-Decomposition

SVDFed: Enabling Communication-Efficient Federated Learning ...

引用

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

作者： Haolin Wang Xuefeng Liu Jianwei Niu Shaojie Tang School of Computer Science and Engineering State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Zhongguancun Laboratory Beijing China School of Information Engineering Zhengzhou University Research Institute of Industrial Technology Zhengzhou University Zhengzhou China Naveen Jindal School Management University of Texas at Dallas Richardson USA

Federated learning (FL) is an emerging paradigm of distributed machine learning. However, when applied to wireless network scenarios, FL usually suffers from high communication cost because clients need to transmit their updated gradients to a server in every training round. Although many gradient compression techniques like sparsification and quantization are proposed, they compress clients’ gradients independently, without considering the correlations among gradients. In this paper, we propose SVDFed, a collaborative gradient compression framework for FL. SVDFed utilizes Singular Value Decomposition (SVD) to find a few basis vectors, whose linear combination can well represent clients’ gradients at a certain round. Due to the correlations among gradients, these basis vectors can still well approximate new gradients in many subsequent rounds. With the help of basis vectors, clients only need to upload the coefficients of the linear combination to the server, which greatly reduces communication cost. In addition, SVDFed leverages the classical PID (Proportional, Integral, Derivative) control to determine the proper time to update basis vectors to maintain their representation ability. Through experiments, we demonstrate that SVDFed outperforms existing gradient compression methods in FL. For example, compared to a popular gradient quantization method QSGD, SVDFed can reduce the communication overhead by 66 % and pending time by 99 %.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration

arXiv

引用

arXiv 2023年

作者： Wu, Xinghao Liu, Xuefeng Niu, Jianwei Zhu, Guogang Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China Jindal School of Management University of Texas Dallas United States

Personalized federated learning (PFL) reduces the impact of non-independent and identically distributed (non-IID) data among clients by allowing each client to train a personalized model when collaborating with others. A key question in PFL is to decide which parameters of a client should be localized or shared with others. In current mainstream approaches, all layers that are sensitive to non-IID data (such as classifier layers) are generally personalized. The reasoning behind this approach is understandable, as localizing parameters that are easily influenced by non-IID data can prevent the potential negative effect of collaboration. However, we believe that this approach is too conservative for collaboration. For example, for a certain client, even if its parameters are easily influenced by non-IID data, it can still benefit by sharing these parameters with clients having similar data distribution. This observation emphasizes the importance of considering not only the sensitivity to non-IID data but also the similarity of data distribution when determining which parameters should be localized in PFL. This paper introduces a novel guideline for client collaboration in PFL. Unlike existing approaches that prohibit all collaboration of sensitive parameters, our guideline allows clients to share more parameters with others, leading to improved model performance. Additionally, we propose a new PFL method named FedCAC, which employs a quantitative metric to evaluate each parameter's sensitivity to non-IID data and carefully selects collaborators based on this evaluation. Experimental results demonstrate that FedCAC enables clients to share more parameters with others, resulting in superior performance compared to state-of-the-art methods, particularly in scenarios where clients have diverse distributions. The code is integrated into our FL training framework: https://***/kxzxvbk/Fling. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

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：