检索结果-内蒙古大学图书馆

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

作者： Jun Dan Weiming Liu Chunfeng Xie Hua Yu Shunjie Dong Yanchao Tan Zhejiang University Queen Mary University of London Dalian University of Technology Shanghai Jiao Tong University Fuzhou University and Engineering Research Center of Big Data Intelligence Ministry of Education and Fujian Key Laboratory of Network Computing and Intelligent Information Processing

ISBN: (纸本)9798331314385

Semi-supervised graph domain adaptation, as a branch of graph transfer learning, aims to annotate unlabeled target graph nodes by utilizing transferable knowledge learned from a label-scarce source graph. However, most existing studies primarily concentrate on aligning feature distributions directly to extract domain-invariant features, while ignoring the utilization of the intrinsic structure information in graphs. Inspired by the significance of data structure information in enhancing models' generalization performance, this paper aims to investigate how to leverage the structure information to assist graph transfer learning. To this end, we propose an innovative framework called TFGDA. Specially, TFGDA employs a structure alignment strategy named STSA to encode graphs' topological structure information into the latent space, greatly facilitating the learning of transferable features. To achieve a stable alignment of feature distributions, we also introduce a SDA strategy to mitigate domain discrepancy on the sphere. Moreover, to address the overfitting issue caused by label scarcity, a simple but effective RNC strategy is devised to guide the discriminative clustering of unlabeled nodes. Experiments on various benchmarks demonstrate the superiority of TFGDA over SOTA methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simple Single-Fed Penta-Band Omnidirectional Antenna with Independent Band Control

引用

IEEE Transactions on Antennas and Propagation 2025年

作者： Zhou, Changfei Gao, Tianyu Zhang, Ruyue Yu, Dapeng Zhang, Wenyu Li, Yingsong Wong, Hang Dalian University of Technology School of Information and Communication Engineering Dalian116024 China Hubei University of Automotive Technology School of Mathematics Physics and Optoelectronic Engineering Shiyan China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230601 China City University of Hong Kong The State Key Laboratory of Terahertz and Millimeter Waves Hong Kong

A novel method of designing a penta-band omnidirectional low-profile antenna with independent band control is proposed. Single-band, dual-band, tri-band, quad-band, and penta-band antennas are investigated, respectively. The proposed penta-band antenna consists of a circular patch, three concentric metal pins, and two square metal plates. The evolutionary step of the penta-band antenna is achieved by adding metal rings and a small metal plate above the big ground. Each of the four metal rings is excited at TM01 mode resonance, while the 5th mode is generated by a small loop resonance formed by the small plate, shorting pin, stub, and the outer conductor of the cable. The penta-band antenna has a small volume of π × (0.109λ1.53GHz)2 × 0.053λ1.53GHz. The corresponding impedance bandwidths (IMBWs) of the five operating bands are 4.9%, 9.4%, 9.0%, 4.8%, 5.0%. Compared with other designs, the proposed antennas exhibit more flexible bands by using a simple structure. Meanwhile, the antenna has a stable omnidirectional radiation pattern across the five bands and a compact size. © 1963-2012 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

Restricted Arc-Connectivity of Unidirectional Star Graphs

SSRN

引用

SSRN 2022年

作者： Zhao, Xiaojun Deng, Qingying Wang, Zhiyi Key Laboratory of Intelligent Computing & Information Processing of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

The restricted arc-connectivity is an effective assessment of the reliability of directed networks, which is an extended notion of arc-connectivity. An arc set S of D is a restricted arc-cut of D if D−S has a strong connected component D′ such that |V (D′)| ≥ 2 and D−V (D′) contains an arc. D is called λ′-connected if there exists a restricted arc-cut in D. The restricted arc-connectivity λ′(D) of a λ′-connected digraph D is the minimum cardinality over all restricted arc-cuts. We can get a unidirectional star graph by orienting the star graph with Day-Tripathi orientation. In this paper, we first show that the restricted arc-connectivity of the n-dimensional unidirectional star graph is n−2 when n is odd and n−3 when n is even for n ≥ 4. As a consequence, we prove that unidirectional star graph is super-λ. © 2022, The Authors. All rights reserved.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Pyramid Convolution and Multi-Frequency Spatial Attention for Fine-Grained Visual Categorization

SSRN

引用

SSRN 2022年

作者： Xu, Qin Li, Yun Zhang, Mengquan Tao, Zhifu Luo, Bin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China School of Big Data and Statistics Anhui University Hefei230601 China

Learning diverse detailed feature is crucial for fine-grained visual categorization (FGVC). However, most of existing methods for FGVC use the standard convolution for feature extraction which leads to the loss of many subtle but important features. Besides, in the existing attention models for FGVC, the features are aggregated by a simple global average pooling operation, which is unable to characterize complex feature information. To address these problems, we propose pyramid convolution and multi-frequency spatial attention (PCMFSA) for FGVC. To capture spatial context dependencies of different levels and avoid the loss of the subtle features, pyramid convolution, which uses convolution kernels with various sizes, is introduced in the backbone network. To reduce the influence of background noise and obtain diverse fine-grained feature information, we propose multi-frequency spatial attention (MFSA) module, in which two channel-wise grouping operations are designed and discrete cosine transform (DCT) in the frequency domain is adopted to enhance features of different spatial positions. Moreover, to mine more valuable regions, peak suppression is used to suppress high-response regions after MFSA. A large number of experimental results show that our method achieves state-of-the-art results on four popularly FGVC datasets. © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

CLSDRL:A routing optimization method for traffic feature extraction

CLSDRL:A routing optimization method for traffic feature ext...

引用

2021 International Conference on Networking and Network Applications, NaNA 2021

作者： Xia, Hong Li, Jianguo Chen, Yanping Lv, Ning Wang, ZhongMin Dong, Qingyi Xi'an University of Posts and Telecommunications School of Computer Science and Technology Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9781665441582

In order to solve the impact of the temporal and spatial characteristics of traffic on network routing optimization, this paper proposes convolution long-short memory neural network deep reinforcement learning (CLSDRL) model for routing optimization. The CLSDRL model consists of deep deterministic policy gradients (DDPG) deep couple with convolution neural network (CNN) and long-short memory neural network (LSTM). After extracting the spatial and temporal characteristics of network traffic with CNN and LSTM, routing decisions are made with DDPG algorithm. Experiments are conducted under different load intensities, and the network performance is evaluated by the average network delay and packet loss rate, experimental results show that this method can improve significantly network performance. © 2021 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Design of Hign Gain Wideband Circular Polarization Antenna Based on All-Metal Vivaldi Antenna 2

A Design of Hign Gain Wideband Circular Polarization Antenna...

引用

2020 2nd International Conference on Artificial Intelligence Technologies and Application, ICAITA 2020

作者： Li, Xuemei Huang, Zhixiang Liu, Dui Wang, Chao Cheng, Yi Key Lab of Intelligent Computing and Signal Processing Ministry of Education AnHui University Heifei AnHui230000 China

This paper designs a broadband circularly polarized antenna covering the 25 GHz to 31 GHz band. The Vivaldi antenna is used as the basic structure to generate broadband electromagnetic waves;circular polarization is achieved by feeding through a circularly polarized bridge;a metal choke ring is used at the bottom to ensure the low side lobes of the antenna. The antenna consists of four basic Vivaldi antennas, a metal choke ring, a grounded substrate, and a feed network. The results show that the antenna covers the entire frequency band when the axial ratio is lower than 3 dB, and the impedance matching is better. The use of a choke ring structure ensures that the antenna electromagnetic waves are radiated upward, resulting in higher gain and lower side lobes. The highest gain in the included frequency band is 11.4 dB, and the simulation result is good. The antenna has high gain and low sidelobe characteristics. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Multi-Granularity Feature Distillation Learning Network for Fine-Grained Visual Classification

Multi-Granularity Feature Distillation Learning Network for ...

引用

Image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Yuhang Cai Xiao Ke Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou Fujian China

ISBN: (纸本)9781665464697

Fine-grained visual classification (FGVC) aims to identify objects belonging to multiple sub-categories of the same super-category (such as species of birds, models of cars and aircraft). The key to solving fine-grained classification problems is to learn discriminative visual feature representation with only subtle differences. Although previous work based on refined feature learning has made great progress, however, high-level semantic features often lack key information for fine-grained visual object nuances. How to efficiently integrate semantic information of different granularities from classification networks is a Critical. In this paper, we propose Multi-Granularity Feature Distillation Learning Network (MGFDL-Net). Our solution integrates multi-granularity hierarchical information through a multi-granularity fusion learning strategy to enhance feature representation. In view of the inherent challenges of large intraclass differences in FGVC, a cross-layer self-distillation regularization is proposed to strengthen the connection between high-level semantics and low-level semantics for robust multi-granularity feature learning. Comprehensive experiments show that our method achieves state-of-the-art performance on three challenging fine-grained visual classification FGVC datasets (CUB-200-2011, Stanford Cars and FGVC-Aircraft).

关键词： Representation learning Visualization Cross layer design Computer vision Image processing Semantics Birds

来源：评论

学校读者我要写书评

暂无评论

Modality-specific Adaptive Scaling Method for Cross-modal Retrieval

Modality-specific Adaptive Scaling Method for Cross-modal Re...

引用

Image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Baitao Chen Xiao Ke Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou Fujian China

ISBN: (纸本)9781665464697

There are huge differences in data distribution and feature representation of different modalities. How to flexibly and accurately retrieve data from different modalities is a challenging problem. The mainstream common subspace method only focus on the heterogeneity gap between modalities, and use a unified method to jointly learn the common representation of different modalities, which can easily lead to the difficulty of multi-modal unified fitting. In this work, we innovatively propose the concept of multi-modal information density discrepancy, and propose a modality-specific adaptive scaling method incorporating prior knowledge, which can adaptively learn the most suitable network for different modalities. Comprehensive experimental results on three widely used cross-modal retrieval datasets show the proposed MASM achieves the state-of-the-art results and significantly outperforms other existing methods.

关键词： Knowledge engineering Computer vision Adaptive systems Image processing Fitting Machine learning

来源：评论

学校读者我要写书评

暂无评论

Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation

arXiv

引用

arXiv 2022年

作者： Shao, Chenze Ma, Zhengrui Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA-Transformer) was recently proposed to model sequential dependency with a directed acyclic graph. Consequently, it has to apply a sequential decision process at inference time, which harms the global translation accuracy. In this paper, we present a Viterbi decoding framework for DA-Transformer, which guarantees to find the joint optimal solution for the translation and decoding path under any length constraint. Experimental results demonstrate that our approach consistently improves the performance of DA-Transformer while maintaining a similar decoding speedup. Copyright © 2022, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Computation Offloading Algorithm Based on Deep Reinforcement Learning and Multi-Task Dependency for Edge computing 25th

Computation Offloading Algorithm Based on Deep Reinforcemen...

引用

25th International Computer Symposium on New Trends in Computer Technologies and Applications, ICS 2022

作者： Lin, Tengxiang Lin, Cheng-Kuan Chen, Zhen Cheng, Hongju College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Department of Computer Science National Yang Ming Chiao Tung University Hsinchu300 Taiwan

ISBN: (纸本)9789811995811

Edge computing is an emerging promising computing paradigm that brings computation and storage resources to the network edge, significantly reducing service latency. In this paper, we aim to divide the task into several sub-tasks through its inherent interrelation, guided by the idea of high concurrency for synchronization, and then offload sub-tasks to other edge servers so that they can be processed to minimize the cost. Furthermore, we propose a DRL-based Multi-Task Dependency Offloading Algorithm (MTDOA) to solve challenges caused by dependencies between sub-tasks and dynamic working scenes. Firstly, we model the Markov decision process as the task offloading decision. Then, we use the graph attention network to extract the dependency information of different tasks and combine Long Short-term Memory (LSTM) with Deep Q Network (DQN) to deal with time-dependent problems. Finally, simulation experiments demonstrate that the proposed algorithm boasts good convergence ability and is superior to several other baseline algorithms, proving this algorithm’s effectiveness and reliability. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement 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：