检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Lin, Jia-Qi Chen, Man-Sheng Zhu, Xi-Ran Wang, Chang-Dong Zhang, Haizhang Sun Yat-sen University Zhuhai China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Computational Science Guangzhou China

Multi-view attributed graph clustering is an important approach to partition multi-view data based on the attribute feature and adjacent matrices from different views. Some attempts have been made in utilizing Graph Neural Network (GNN), which have achieved promising clustering performance. Despite this, few of them pay attention to the inherent specific information embedded in multiple views. Meanwhile, they are incapable of recovering the latent high-level representation from the low-level ones, greatly limiting the downstream clustering performance. To fill these gaps, a novel Dual Information enhanced multi-view Attributed Graph Clustering (DIAGC) method is proposed in this paper. Specifically, the proposed method introduces the Specific Information Reconstruction (SIR) module to disentangle the explorations of the consensus and specific information from multiple views, which enables GCN to capture the more essential low-level representations. Besides, the Mutual Information Maximization (MIM) module maximizes the agreement between the latent high-level representation and low-level ones, and enables the high-level representation to satisfy the desired clustering structure with the help of the Self-supervised Clustering (SC) module. Extensive experiments on several real-world benchmarks demonstrate the effectiveness of the proposed DIAGC method compared with the state-of-the-art baselines. Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural Networks

arXiv

引用

arXiv 2022年

作者： Tang, Jianxiong Lai, Jianhuang Xie, Xiaohua Yang, Lingxiao Zheng, Wei-Shi The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China The Guangdong Province Key Laboratory of Information Security Technology Sun Yat-Sen University Guangzhou China The Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Spiking neural networks are efficient computation models for low-power environments. Spike-based BP algorithms and ANN-to-SNN (ANN2SNN) conversions are successful techniques for SNN training. Nevertheless, the spike-base BP training is slow and requires large memory costs. Though ANN2NN provides a low-cost way to train SNNs, it requires many inference steps to mimic the well-trained ANN for good performance. In this paper, we propose a SNN-to-ANN (SNN2ANN) framework to train the SNN in a fast and memory-efficient way. The SNN2ANN consists of 2 components: a) a weight sharing architecture between ANN and SNN and b) spiking mapping units. Firstly, the architecture trains the weight-sharing parameters on the ANN branch, resulting in fast training and low memory costs for SNN. Secondly, the spiking mapping units ensure that the activation values of the ANN are the spiking features. As a result, the classification error of the SNN can be optimized by training the ANN branch. Besides, we design an adaptive threshold adjustment (ATA) algorithm to address the noisy spike problem. Experiment results show that our SNN2ANN-based models perform well on the benchmark datasets (CIFAR10, CIFAR100, and Tiny-ImageNet). Moreover, the SNN2ANN can achieve comparable accuracy under 0.625× time steps, 0.377× training time, 0.27× GPU memory costs, and 0.33× spike activities of the Spike-based BP model. Code is available at https://***/TJXTT/SNN2ANN. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Conditional Image Hiding Network Based on Style Transfer

SSRN

引用

SSRN 2023年

作者： Zhang, Fenghua Feng, Bingwen Xia, Zhihua Weng, Jian Lu, Wei Chen, Bin College of Information Science and Technology Jinan University Guangzhou510632 China School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China School of Cyber Security Guangdong Polytechnic Normal University Guangzhou510665 China

Various data hiding methods have been suggested to hide secret images within stego images. However, many of them could be easily detected by steganalytic tools due to their large hiding information. In this paper, we enhance the undetectability of image hiding network by mapping latent representation conditional on secret information. We extend the idea of image generation-based steganography and propose a Transformer-based image hiding network that can hide a secret image with the same size as the target image. The proposed scheme uses style transferring to help map latent representation. The hiding network of the proposed scheme consists of three modules: encoding, transfer, and synthesis modules. The encoding module extracts the latent representations from content and secret images, the transfer module stylizes the latent representation, and the synthesis module fuses the the latent representations to synthesize a target image with the secret image hidden in it. A new synthesis module as well as the corresponding extraction network is designed to improve recovery accuracy. The proposed scheme shows high image quality on both target images and recovered secret images. Furthermore, it can resist steganalytic tools and thus provides good security. © 2023, The Authors. All rights reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Edge Graph intelligence: Reciprocally Empowering Edge Networks With Graph intelligence

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Zeng, Liekang Ye, Shengyuan Chen, Xu Zhang, Xiaoxi Ren, Ju Tang, Jian Yang, Yang Shen, Xuemin Sherman Sun Yat-sen University School of Computer Science and Engineering Guangzhou510275 China Guangzhou511453 China Ministry of Education School of Computer Science and Engineering Sun Yat-sen University The Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou510275 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Midea Group Shanghai201702 China Guangzhou511453 China Peng Cheng Laboratory Shenzhen518055 China Terminus Group Beijing100027 China University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Recent years have witnessed a thriving growth of computing facilities connected at the network edge, cultivating edge networks as a fundamental infrastructure for supporting miscellaneous intelligent services. Meanwhile, Artificial intelligence (AI) frontiers have extrapolated to the graph domain and promoted Graph intelligence (GI). Given the inherent relation between graphs and networks, the interdiscipline of graph learning and edge networks, i.e., Edge GI or EGI, has revealed a novel interplay between them - GI aids in optimizing edge networks, while edge networks facilitate GI model deployment. Driven by this delicate closed-loop, EGI is recognized as a promising solution to fully unleash the potential of edge computing power and is garnering growing attention. Nevertheless, research on EGI remains nascent, and there is a soaring demand within both the communications and AI communities for a dedicated venue to share recent advancements. To this end, this paper promotes the concept of EGI, explores its scope and core principles, and conducts a comprehensive survey concerning recent research efforts on this emerging field. Specifically, this paper introduces and discusses: 1) fundamentals of edge computing and graph learning, 2) emerging techniques centering on the closed loop between graph intelligence and edge networks, and 3) open challenges and research opportunities of future EGI. By bridging the gap across communication, networking, and graph learning areas, we believe that this survey can garner increased attention, foster meaningful discussions, and inspire further research ideas in EGI. © 1998-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Mdpnet:A Dual-Pathway Parallel Fusion Network for Multi-Modal MRI Glioma Genotyping

SSRN

引用

SSRN 2024年

作者： Wang, Huaizhi Liu, Haichao Du, Fang Wang, Di Song, Lijuan School of Information Engineering Ningxia University Ningxia Hui Autonomous Region Yinchuan750021 China School of Advanced Interdisciplinary Studies Ningxia University Ningxia Hui Autonomous Region Zhongwei755000 China Ningxia Key Laboratory of Artificial Intelligence and Information Security for Channeling Computing Resources from the East to the West Ningxia Yinchuan750021 China Collaborative Innovation Center for Ningxia Big Data and Artificial Intelligence Co-founded by Ningxia Municipality and Ministry Ningxia Yinchuan750021 China

Glioblastomas have become the most lethal brain tumors in humans, and accurate diagnosis of gliomas is crucial for patient treatment and prognosis. Magnetic Resonance Imaging (MRI) is widely used due to its non-invasiveness and convenience. However, due to the significant heterogeneity of gliomas, even experienced neuroradiologists find it challenging to accurately differentiate glioma types based on imaging phenotypes. According to the WHO classification of central nervous system tumors, the types of gliomas can be determined based on the status of IDH, 1p/19q, and ATRX genetic markers. Current research is mostly limited to the analysis of a single molecular marker, either IDH or 1p/19q, lacking a comprehensive model to simultaneously evaluate these three critical molecular markers. Moreover, the lesion information embedded in T2 and FLAIR modalities has not been fully utilized, thus limiting the accuracy of glioma *** address this issue, we designed a dual-pathway parallel fusion network for multi-modal MRI glioma genotyping (MDPNet), which can simultaneously genotype IDH, 1p/19q, and ATRX genetic markers. MDPNet mainly consists of two parts: attention-guided asymmetric dual-pathway feature extraction (ADFE) and inter-gene relationship-guided genotyping (IGT). ADFE integrates CNN and attention mechanisms to capture both global and local information, enhancing the information from T2 and FLAIR modalities and extracting complex feature information through two parallel pathways. IGT constructs a complex classifier based on the interrelations among genes to simultaneously predict IDH mutation status, 1p/19q co-deletion status, and ATRX mutation *** evaluated our model on public datasets, and experimental results showed that our proposed method exhibited excellent performance. Ablation experiments demonstrated that utilizing the typing information of IDH and ATRX not only improved the network's performance in typing the 1p/19q gene molecule but also furt

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Discriminative distillation to reduce class confusion in continual learning

arXiv

引用

arXiv 2021年

作者： Zhong, Changhong Cui, Zhiying Wang, Ruixuan Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou510000 China

Successful continual learning of new knowledge would enable intelligent systems to recognize more and more classes of objects. However, current intelligent systems often fail to correctly recognize previously learned classes of objects when updated to learn new classes. It is widely believed that such downgraded performance is solely due to the catastrophic forgetting of previously learned knowledge. In this study, we argue that the class confusion phenomena may also play a role in downgrading the classification performance during continual learning, i.e., the high similarity between new classes and any previously learned classes would also cause the classifier to make mistakes in recognizing these old classes, even if the knowledge of these old classes is not forgotten. To alleviate the class confusion issue, we propose a discriminative distillation strategy to help the classify well learn the discriminative features between confusing classes during continual learning. Experiments on multiple natural image classification tasks support that the proposed distillation strategy, when combined with existing methods, is effective in further improving continual learning. Copyright © 2021, The Authors. All rights reserved.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-task Cascaded Acoustic Echo Cancellation and Noise Suppression

Deep Multi-task Cascaded Acoustic Echo Cancellation and Nois...

引用

International Symposium on Chinese Spoken Language Processing

作者： Junjie Li Meng Ge Longbiao Wang Jianwu Dang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Huiyan Technology (Tianjin) Co. Ltd Tianjin China Japan Advanced Institute of Science and Technology Ishikawa Japan

ISBN: (纸本)9798350397970

With the growing need for online communication, removing the acoustic echo and background noise during voice and video calls has become a major problem. Recent studies show that deep learning based algorithms can successfully be applied to acoustic echo cancellation. These algorithms usually use one mask to remove acoustic echo and noise at the same time. Considering the patterns of acoustic echo and noise are different, hence we propose a multi-task cascaded framework with multiple masks named DMC-AEC to ease the difficulty of removing different interference, i.e., acoustic echo and noise. The DMC-AEC consists of three cascaded blocks, each block containing one mask. The first block takes mic and far-end signals to learn the auxiliary task of estimating the echo. The second block utilizes the estimated echo, far-end and mic signals to cancel acoustic echo. And in the third block, it takes the output of the second block and further suppresses noise. The DMC-AEC is trained on a synthetic dataset of ICASSP AEC Challenge.

关键词： Training Deep learning Microwave integrated circuits Echo cancellers Noise reduction Interference Multitasking

来源：评论

学校读者我要写书评

暂无评论

Preference-Guided Reinforcement Learning for Efficient Exploration

arXiv

引用

arXiv 2024年

作者： Wang, Guojian Wu, Faguo Zhang, Xiao Chen, Tianyuan Chen, Xuyang Zhao, Lin The School of Mathematical Sciences Beihang University Beijing100191 China The Key Laboratory of Mathematics Informatics and Behavioral Semantics Ministry of Education Beijing100191 China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing100194 China The Institute of Artificial Intelligence Beihang University Beijing100191 China The Department of Electrical and Computer Engineering National University of Singapore 117583 Singapore

In this paper, we investigate preference-based reinforcement learning (PbRL) that allows reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not feasible. However, this approach is inefficient and impractical for promoting deep exploration in hard-exploration tasks with long horizons and sparse rewards. To tackle this issue, we introduce LOPE: Learning Online with trajectory Preference guidancE, an end-to-end preference-guided RL framework that enhances exploration efficiency in hard-exploration tasks. Our intuition is that LOPE directly adjusts the focus of online exploration by considering human feedback as guidance, avoiding learning a separate reward model from preferences. Specifically, LOPE includes a two-step sequential policy optimization process consisting of trust-region-based policy improvement and preference guidance steps. We reformulate preference guidance as a novel trajectory-wise state marginal matching problem that minimizes the maximum mean discrepancy distance between the preferred trajectories and the learned policy. Furthermore, we provide a theoretical analysis to characterize the performance improvement bound and evaluate the LOPE’s effectiveness. When assessed in various challenging hard-exploration environments, LOPE outperforms several state-of-the-art methods regarding convergence rate and overall performance. The code used in this study is available at https://***/buaawgj/LOPE. Copyright © 2024, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Target-Oriented WiFi Sensing for Respiratory Healthcare: from Indiscriminate Perception to In-Area Sensing

引用

IEEE Network 2024年

作者： Wang, Meng Huang, Jinyang Zhang, Xiang Liu, Zhi Li, Meng Zhao, Peng Yan, Huan Sun, Xiao Dong, Mianxiong Hefei University of Technology Anhui Province Key Laboratory of Affective Computing and Advanced Intelligence Machine School of Computer and Information Hefei230601 China University of Science and Technology of China CAS Key Laboratory of Electromagnetic Space Information Hefei230026 China The University of Electro-Communications Department of Computer and Network Engineering Tokyo1828585 Japan Guizhou Normal University School of Big Data and Computer Science Guiyang550025 China Muroran Institute of Technology Department of Sciences and Informatics 0508585 Japan

Driven by the vision of integrated sensing and communication (ISAC) toward 6G technology, the WiFi-based respiration sensing approach has emerged as a highly competitive candidate for advanced healthcare services. Nevertheless, the indiscriminate perception of all the moving objects within the sensing area raises challenges for system stability and robustness for real-world deployment, especially for the susceptibility to motion interference from other people. Meanwhile, thanks to the emerging in-area wireless sensing technologies, i.e., beamforming, the dynamic environment tolerance of these technologies gives crucial opportunities for target-oriented WiFi-based healthcare services. This article discusses the compelling intersection of in-area WiFi sensing and the future of target-oriented intelligent respiratory healthcare network services. We first present a novel WiFi-based healthcare-assisting framework tailored for inter-user motion interference-tolerable (IMIT) sensing. The detailed components of low-level signal preprocessing, target-direction signal extraction, and healthcare-related services are discussed. By utilizing CSI beamforming technology, which adjusts a directional beam toward the desired direction and adaptively places beam nulls in noisy directions, we can mitigate motion interference and achieve target-oriented healthcare sensing. Finally, we discuss open challenges and potential solutions for target-oriented WiFi healthcare sensing. © 1986-2012 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Efficient meta neural heuristic for multi-objective combinatorial optimization 23

Efficient meta neural heuristic for multi-objective combinat...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Jinbiao Chen Jiahai Wang Zizhen Zhang Zhiguang Cao Te Ye Siyuan Chen School of Computer Science and Engineering Sun Yat-sen University P.R. China School of Computer Science and Engineering Sun Yat-sen University P.R. China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University P.R. China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R. China School of Computing and Information Systems Singapore Management University Singapore

Recently, neural heuristics based on deep reinforcement learning have exhibited promise in solving multi-objective combinatorial optimization problems (MOCOPs). However, they are still struggling to achieve high learning efficiency and solution quality. To tackle this issue, we propose an efficient meta neural heuristic (EMNH), in which a meta-model is first trained and then fine-tuned with a few steps to solve corresponding single-objective subproblems. Specifically, for the training process, a (partial) architecture-shared multi-task model is leveraged to achieve parallel learning for the meta-model, so as to speed up the training; meanwhile, a scaled symmetric sampling method with respect to the weight vectors is designed to stabilize the training. For the fine-tuning process, an efficient hierarchical method is proposed to systematically tackle all the subproblems. Experimental results on the multi-objective traveling salesman problem (MOTSP), multi-objective capacitated vehicle routing problem (MOCVRP), and multi-objective knapsack problem (MOKP) show that, EMNH is able to outperform the state-of-the-art neural heuristics in terms of solution quality and learning efficiency, and yield competitive solutions to the strong traditional heuristics while consuming much shorter time.

关键词：

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：