检索结果-内蒙古大学图书馆

IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)

作者： Yin, Yuexi Zhuang, Zirui Wang, Jingyu Qi, Qi Sun, Haifeng Fu, Xiaoyuan Liao, Jianxin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350350128

In the imminent era of 6G, Quality of Service (QoS) emerges as a pivotal concern in wireless communications. The prescribed transmission rates and vast access demands mandated by 6G standards impose heightened requirements on network throughput and delay. However, the highly dynamic and often bursty nature of application demands presents challenges for routing and congestion control. The backpressure-based joint rate and routing control algorithm adaptively adjusts network traffic to achieve optimal throughput. However, varying traffic conditions hinder the algorithm's convergence to ideal states. Additionally, relying solely on first-order backlog differences for forwarding can lead to poor convergence and high delays. In this study, we propose a Second-Order Smooth Backpressure (SoSBP) algorithm, leveraging second-order backlog metrics and dual-level queue mapping, to address throughput, delay, and jitter issues in dynamic network environments. We validate the efficacy of this novel backlog metric using Lyapunov optimization techniques. Simulation results demonstrate that our approach significantly reduces end-to-end delay and data jitter while preserving throughput and eliminating routing loops.

关键词： Backpressure routing Delay reduction Lyapunov optimization Jitter Queueing

来源：评论

学校读者我要写书评

暂无评论

High-Level Attention Meta-Learner for Class Incremental Learning

High-Level Attention Meta-Learner for Class Incremental Lear...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Tian, Yingjian Wang, Hongbo Chen, Xuhong Li, Yuanhao Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Human beings can continuously improve themselves to achieve new goals depending on their environment. Based on this situation, researchers are constantly optimizing machine learning models to enable them to have similar capabilities as humans. As one of the research areas, class incremental learning aims to learn new tasks over time without forgetting. In addition, the aim of meta learning is to integrate the knowledge learned in the past and adapt to the current task more quickly. Based on the above, we use meta learning to alleviate the catastrophic forgetting problem in class incremental learning. We propose a method, named High-Level Attention Meta-Learner (HLAML), which learns shared parameters of all tasks and predicts the task automatically. HLAML contains an attention module at the high-level of the network which can extract task information, thus helping the model to better distinguish past tasks. Furthermore, for the attention module, we design a task loss function to help the attention module better extract task-related features. Our model achieves excellent performances on MNIST, SVHN, CIFAR10, CIFAR100, ImageNet100, and ImageNet1000.

关键词： class incremental learning meta learning attention mechanism catastrophic forgetting continual learning

来源：评论

学校读者我要写书评

暂无评论

MO-FreeVM: multi-objective server release algorithm for cluster resource management

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2023年第2期26卷 1011-1034页

作者： Zhang, Shiyan Zhang, Yuchao Wang, Ran Gong, Xiangyang Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol 10 Xitucheng Rd Beijing 100089 Peoples R China

With the rise of 5G/6G and cloud computing, cluster management has become increasingly popular. Elastic cluster resources allow cloud clients to dynamically scale their resource requirements over time. Existing researches of cluster schedulers focus on improving resource scheduling speed, increasing cluster utilization, compacting the number of active physical machines (PMs) and time satisfaction function (TSF) within a cluster. The TSF is applied as a time to measure the parallel-VM scheduling problem. However, completing execution time (makespan) of task requests is often neglected, which results in inaccurate scheduling and unreasonable total cost computation. The total cost involves PM cost, migrate cost, and balance cost. To solve the problem of inaccurate scheduling of task requests and total cost billing in cluster management, in this paper, we propose an innovative heuristic algorithm, namely, multi-objective two-stage variable neighborhood searching (MO_STVNS), which aims at minimizing total cost while also considering TSF for active PMs. Moreover, we design a Multi-Objective FreeVM (MO-FreeVM) scheduler based on resource prediction, which incorporates a variety of algorithms to work in collaboration to provide near-optimal resource management for cluster. We evaluate MO_STVNS in different real traces and measure it through extensive experiments. The experimental results show that compared with state-of-art methods, the average total cost and average TSF of MO_STVNS are reduced by 33.75% and 60.67% respectively.

关键词： Cluster management Cloud Multi-objective Virtual machine Scheduling

来源：评论

学校读者我要写书评

暂无评论

An Implicit Relationship Extraction Model Based on Improved Attention and Gated Decoding for Intent Recognition and Slot Filling

An Implicit Relationship Extraction Model Based on Improved ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ge, Shuo Lin, Rongheng Zou, Hua Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350359329;9798350359312

In the context of natural language understanding for short texts, pipeline and joint learning models based on deep learning are two common approaches to address the challenges of intent recognition and slot filling. Due to the potential error propagation behavior of the pipeline model, its final effectiveness is often compromised by deviations in the initial stage. Although there have been some endeavors and contributions in the domain of intent recognition within joint learning, most methods do not explicitly focus on establishing the relationship between intent and slot. We propose a novel joint recognition model for intent and slot which incorporates an enhanced self-attention mechanism and a weight gating unit channel. This channel effectively extracts the correlation between intent and slot during the decoding process. Our model is evaluated on public datasets like ATIS and SNIPS, demonstrating an approximate 1.0% improvement in accuracy compared to the current mainstream models that utilize attention-based methods.

关键词： Intent recognition Slot filling Self-attention Joint learning

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Method Based on Distributed Online Collaborative Distillation 13th

Fault Diagnosis Method Based on Distributed Online Collabora...

引用

13th International Conference on Computer Engineering and Networks (CENet)

作者： Long, Yuhan Yang, Yang Fan, Chengwen Gao, Zhipeng Rui, Lanlan Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9789819992454;9789819992430;9789819992423

Distributed networks and systems are becoming more and more widespread and practical in applications. The distributed network has a large scale and a large number of edge terminals, which generate massive data during operation. As far as fault diagnosis is concerned, traditional techniques face many challenges. The paper proposes a Fault Diagnosis Method Based on Distributed Online Collaborative Distillation (DOCD) for distributed and decentralized scenes. To adapt to the large-scale distributed network and the unstable communication quality scenario, the method distributes the training tasks among the terminal nodes to eliminate the strong dependence of each terminal on the cloud server. Each terminal processes the local data separately and trains the fault diagnosis model locally. Through online optimized collaborative distillation, each terminal model exchanges information and knowledge to improve the diagnostic capability of global data. Finally, the effectiveness of the proposed method is proved by experiments.

关键词： Fault diagnosis Knowledge distillation Distributed network Collaborative distillation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Support Information Mining for Category-Agnostic Pose Estimation

Dynamic Support Information Mining for Category-Agnostic Pos...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Ren, Pengfei Gao, Yuanyuan Sun, Haifeng Qi, Qi Wang, Jingyu Liao, Jianxin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Category-agnostic pose estimation (CAPE) aims to predict the pose of a query image based on few support images with pose annotations. Existing methods achieve the localization of arbitrary keypoints through similarity matching between support keypoint features and query image features. However, these methods primarily focus on mining information from the query images, neglecting the fact that support samples with keypoint annotations contain rich category-specific fine- grained semantic information and prior structural information. In this paper, we propose a Support-based Dynamic Perception Network (SDP-Net) for the robust and accurate CAPE. On the one hand, SDPNet models complex dependencies between support keypoints, constructing category-specific prior structure to guide the interaction of query keypoints. On the other hand, SDPNet extracts fine-grained semantic information from support samples, dynamically modulating the refinement process of query. Our method outperforms existing methods on MP-100 dataset by a large margin.

关键词： Category-agnostic Pose Estimation

来源：评论

学校读者我要写书评

暂无评论

LogNotion: Highlighting Massive Logs to Assist Human Reading and Decision Making

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2025年第2期18卷 940-953页

作者： Chu, Guojun Wang, Jingyu Sun, Tao Qi, Qi Sun, Haifeng Zhuang, Zirui Liao, Jianxin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China China Mobile Res Inst Beijing 100053 Peoples R China

Massive logs contain crucial information about the working status of software systems, which contributes to anomaly detection and troubleshooting. For engineers, it is a laborious task to manually inspect raw logs to know the system running status, and therefore an automated log summarization tool can be helpful. However, due to the specificity of logs in terms of grammar, vocabulary and semantics, existing natural language-based methods cannot perform well in log analysis. To address these issues, we propose LogNotion, a general log summarization framework that highlights the log messages to assist human reading and decision making. We first explore the role played by triplets in log analysis, and propose a triplet extraction method based on sequence tagging and component alignment, in which the specificity of logs is fully taken into account. Then, we propose an unsupervised log summarization method to extract both regular and noteworthy information based on triplets. Comprehensive experiments are conducted on seven real-world log datasets and the results show that LogNotion improves the average ROUGE-1 by 0.26, recall by 0.12, and compression ratio by 2.13%, compared to state-of-the-art log summarization tools. The helpfulness, readability and generalizability are also verified through human evaluation and cross-dataset tests.

关键词： Sun Natural languages Decision making Semantics Manuals Large-scale systems Inspection Grammar Codes Analytical models Log analysis triplet extraction system comprehension log summarization

来源：评论

学校读者我要写书评

暂无评论

Dynamic Beam Pattern Based on Cooperation Multi-Agent VDN-D3QN for LEO Satellite Communication System

IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING

引用

IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND networking 2025年第2期9卷 725-738页

作者： Meng, Meng Hu, Bo Chen, Shanzhi Kang, Shaoli Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100088 Peoples R China China Acad Telecommun Technol State Key Lab Wireless Mobile Commun Beijing 100083 Peoples R China

Due to the cooperative coverage characteristic of LEO satellites and non-uniform traffic demand of beam positions, allocating the limited beam and power resource to massive beam positions flexibly and effectively is a challenge in beam hopping LEO satellite communication system. The agents in existing beam hopping schemes, which rely on deep reinforcement learning, are limited to acquiring state information within the coverage area of LEO satellite. For this reason, we propose a cooperation multi-agent Value-Decomposition Networks with Dueling Double Deep Q-Learning Network (VDN-D3QN) framework to generate dynamic beam hopping pattern for assuring delay fairness and throughput among beam positions in LEO satellite communication system. The proposed VDN-D3QN dynamic beam hopping method is divided into training and test phase, where each agent is only responsible for the beam hopping pattern of one LEO satellite. During the train phase, the agents learn to cooperate with other agents to maximize the system throughput and minimize the delay fairness among beam positions by Dueling Double Deep Q-Learning Network. Then, the Value-Decomposition Networks is employed to learn the optimal policy in a centralized manner through interaction with the environment. In test phase, the trained agents are deployed to address the challenging problem of inter-satellite communication in a distributed manner, and one agent is deployed per LEO satellite. The trained agents can make decisions about the dynamic beam hopping pattern based on the available local state information in LEO satellite communication system. The evaluation results demonstrate that the proposed multi-agent VDN-D3QN algorithm can effectively handle the non-uniform traffic demand of multi-satellites simultaneously. Besides, the simulation results indicate that the proposed VDN-D3QN algorithm can allocate resource intelligently for adapting the requirements of beam positions and achieving better performance compared to

关键词： Satellites Low earth orbit satellites Satellite communications Resource management Throughput Optimization Delays Beam hopping deep reinforcement learning D3QN VDN LEO satellite

来源：评论

学校读者我要写书评

暂无评论

Semantic-Importance-Aware Reordering-Enhanced Semantic Communication System With OFDM Transmission

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第7期12卷 7938-7954页

作者： Liu, Yucheng Dong, Chen Liang, Haotai Li, Weizhi Bao, Zhicheng Zheng, Zhe Xu, Xiaodong Zhang, Ping Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Peng Cheng Lab Dept Broadband Commun Shenzhen 518066 Guangdong Peoples R China

As a novel communication paradigm, semantic communication (SemCom) can greatly improve communication efficiency, which has aroused extensive research by scholars worldwide. As one of the important aspects of digital communication nowadays, how to combine channel estimation with SemCom is an important research direction. In this article, based on orthogonal frequency-division multiplexing (OFDM) communication architecture, the semantic importance-aware reordering-enhanced SemCom system (SIARE-SC) is proposed, which utilizes the inequality of semantic symbols combined with channel estimation in OFDM systems to reduce the distortion caused by channel estimation interpolation error (CEIE) and further improve the signal recovery quality. To enhance the generalizability of the system, we extend the verification of the effectiveness of SIARE-SC in various scenarios with different sources, channels, and pilot patterns. Furthermore, the importance reordering method proposed in the SIARE-SC has good applicability and effectiveness, which can be used to be compatible with other SemCom systems and has a significant suppression effect on the peak-to-average power ratio (PAPR). Meanwhile, CEIE has been considered for the first time to be included in the analysis of SemCom distortion, and mathematically derive the performance expressions of SIARE-SC under different channel and pilot pattern scenarios from three perspectives, namely, channel bandwidth ratio (CBR), signal-to-noise ratio (SNR), and CEIE, to obtain the corresponding bound of performance. The proposed SIARE-SC is shown to significantly improve semantic performance in various scenarios by conducting a large number of experimental tests.

关键词： Semantics Channel estimation Symbols OFDM Entropy Training Fading channels Semantic communication Upper bound Transforms orthogonal frequency-division multiplexing (OFDM) pilot pattern semantic communication (SemCom) semantic importance

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC DESIGN OF ADAPTER ARCHITECTURES FOR ENHANCED PARAMETER-EFFICIENT FINE-TUNING 49

AUTOMATIC DESIGN OF ADAPTER ARCHITECTURES FOR ENHANCED PARAM...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xu, Siya Wen, Xinyan Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Adapters, one of the most important parameter-efficient fine-tuning (PEFT) methods, achieve state-of-the-art (SOTA) performance through manual architecture design. To unlock the full potential of adapter tuning, we introduce the AutoAdapter framework, designated to design novel adapter architectures automatically. First, we discuss the adapter design choices and define a search space. Second, we propose C-DARTS, an contribution-based differentiable neural architecture search (NAS) method, to enhance the search results. We conduct comprehensive experiments and analysis on the GLUE and SuperCLUE benchmark tasks, demonstrating that AutoAdapter effectively designs novel adapters that outperform recent baseline PEFT methods.

关键词： Adapters Parameter-efficient fine-tuning Neural architecture search pretrained language models

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：