检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Shao, Chenze Zhang, Jinchao Zhou, Jie Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Pattern Recognition Center WeChat AI Tencent Inc China

Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate for the training when the NAT output is closer to other translations. In response to this problem, we introduce a rephraser to provide a better training target for NAT by rephrasing the reference sentence according to the NAT output. As we train NAT based on the rephraser output rather than the reference sentence, the rephraser output should fit well with the NAT output and not deviate too far from the reference, which can be quantified as reward functions and optimized by reinforcement learning. Experiments on major WMT benchmarks and NAT baselines show that our approach consistently improves the translation quality of NAT. Specifically, our best variant achieves comparable performance to the autoregressive Transformer, while being 14.7 times more efficient in inference. Copyright © 2022, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Towards Distractibility Induced trust Management Using BlockChain for Edge computing

Towards Distractibility Induced trust Management Using Block...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2021

作者： Yang, Haochen Wang, Guanghui Dong, Lifeng He, Xin School of Software Henan University Kaifeng China Henan Provincial Engineering Research Center of Intelligent Data Processing Kaifeng China Henan International Joint Laboratory of Intelligent Network Theory and Key Technology Henan University Kaifeng China Institute of Intelligent Network System Henan University Kaifeng China Henan Jiuyu Tenglong Information Engineering Co. Ltd. Zhengzhou China

ISBN: (纸本)9789811669620

Edge computing solves massive data processing problems by utilizing the storage and computing functions of edge devices. Due to the openness of edge computing, distracted devices inevitably participate in edge computing and affect the network computing performance, which degrades trust management of edge devices. To solve the above issue, this paper proposes a trust management framework based on blockchain for edge computing scenarios (ECTMF). First, the ECTMF framework slices users and provides corresponding services based on different requirements. It evaluates the trustworthiness of end devices and distinguishes distracted devices in edge computing. Then, the Proof of Monitor (PoM) consensus mechanism is proposed to continuously monitor distracted end devices in edge computing. Simulations validate the effectiveness and efficiency of the ECTMF and PoM. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Tail Classes Matter: Long-Tailed Object Detection Revisited

Tail Classes Matter: Long-Tailed Object Detection Revisited

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yinglu Zhang Chenbo Zhang Lu Zhang Tianying Liu Jihong Guan Xinkai Liang Jiajia Zhao Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University China Department of Computer Science & Technology Tongji University China Science and Technology on Complex System Conroland InelligentAgent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute China

Real-world data ubiquitously exhibit long-tailed distribution, which sparks the increasing interest in long-tailed object detection (LTOD). However, existing methods neglect that a lack of diverse data in tail classes will cause underrepresented tail class features, making their efforts for balancing foreground classes tend to over-fit tail classes and be less effective. In this paper, we propose a multi-class co-attention generation network to increase data diversity of tail classes by generating augmented samples. To alleviate imbalance, we develop a distribution-aware up-sampling strategy, performing differential up-sampling for different classes and design a bi-directional regulation loss to adjust both positive and negative gradients. Moreover, we construct a new dataset LVIS-X with more rare classes based on existing LTOD benchmark dataset LVIS. Experiments on LVIS and LVIS-X demonstrate the superiority of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition of Virtual Reality Scenes Under Olfactory Stimulation: An ECG Study

SSRN

引用

SSRN 2023年

作者： Liu, Wanqing Zhong, Xinyue Feng, Weibin Xie, Jialan Luo, Yutong Guangyuan, Liu College of Electronic and Information Engineering Southwest University Chongqing400715 China Institute of Affective Computing and Intelligent Information Processing Southwest University Chongqing400715 China Key Laboratory of Cognition and Personality Ministry of Education Faculty of Psychology Southwest University Chongqing400715 China

Virtual Reality (VR) technology enhanced by olfactory stimulation has introduced novel dimensions to human-computer interaction (HCI). While there have been studies utilizing electrocardiogram (ECG) signals to explore the impact of olfaction on the emotional experiences of traditional multimedia users, little research has delved into the influence of heightened olfactory stimulation on emotion recognition within virtual reality scenarios. To explore this issue in depth, we first initiated an olfactory stimulation experiment within a VR environment, collecting ECG data from 65 participants as they interacted with VR scenes and olfactory-enhanced virtual reality (OVR) scenes, each characterized by varying emotional valence and levels of emotional arousal. Subsequently, we extracted time-domain, frequency-domain, and nonlinear features from the ECG data. Finally, we employed three widely used machine learning classification models, namely, light gradient boosting machine, SVM, and adaptive enhancement algorithm, to discern the emotional valence and arousal levels in OVR and VR states, respectively. The results indicate that the classification recognition rates of all three classifiers are significantly higher (> 4%) within the OVR environment than in the VR context, both in terms of valence and arousal dimensions. The results are consistent with the analysis and comparison of behavioral data. This finding underscores the capacity of ECG data to effectively capture distinctions in emotional responses between OVR and VR experiences and highlights the contributory role of olfactory enhancement in VR-based emotion recognition. Our discoveries will contribute to the advancement of OVR emotion recognition research and offer fresh insights for enhancing the overall HCI emotional experience. © 2023, The Authors. All rights reserved.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Explainable Semantic Federated Learning Enabled Industrial Edge Network for Fire Surveillance

arXiv

引用

arXiv 2024年

作者： Dong, Li Peng, Yubo Jiang, Feibo Wang, Kezhi Yang, Kun School of Computer Science Hunan University of Technology and Business Changsha410205 China Xiangjiang Laboratory Changsha410205 China School of Intelligent Software and Engineering Nanjing University Suzhou China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China Department of Computer Science Brunel University London United Kingdom

In fire surveillance, Industrial Internet of Things (IIoT) devices require transmitting large monitoring data frequently, which leads to huge consumption of spectrum resources. Hence, we propose an Industrial Edge Semantic Network (IESN) to allow IIoT devices to send warnings through Semantic communication (SC). Thus, we should consider (1) Data privacy and security. (2) SC model adaptation for heterogeneous devices. (3) Explainability of semantics. Therefore, first, we present an eXplainable Semantic Federated Learning (XSFL) to train the SC model, thus ensuring data privacy and security. Then, we present an Adaptive Client Training (ACT) strategy to provide a specific SC model for each device according to its Fisher information matrix, thus overcoming the heterogeneity. Next, an Explainable SC (ESC) mechanism is designed, which introduces a leakyReLU-based activation mapping to explain the relationship between the extracted semantics and monitoring data. Finally, simulation results demonstrate the effectiveness of XSFL. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

CSCL-DTI: predicting drug-target interaction through cross-view and self-supervised contrastive learning

CSCL-DTI: predicting drug-target interaction through cross-v...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xuan Lin Xi Zhang Zu-Guo Yu Yahui Long Xiangxiang Zeng Philip S. Yu College of Computer Science Xiangtan University China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University China Singapore Immunology Network (SIgN) Agency for Science Technology and Research (A*STAR) Singapore College of Information Science and Engineering Hunan University China Department of Computer Science University of Illinois Chicago USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Accurately predicting drug-target interactions (DTI) is a critical step in drug discovery. Existing methods of DTI prediction primarily employ Simplified Molecular-Input Line-Entry System (SMILES) sequences or molecular graphs to learn drug representations. However, the features learned by such single-view approach is prone to incomplete. While some multiview methods that consider the views of both SMILES sequences and molecular graphs have been developed, these methods often fall in short in capturing potential interactions between views. In this work, we propose a novel dual contrastive learning framework CSCL-DTI for DTI prediction. First, we design a contrastive-enhanced cross-view representation learning (CVRL) to learn representations for drugs. In this module, Transformer-based and graph convolutional network (GCN)-based encoders are separately adopted to learn view-specific representations, followed by contrastive learning to enrich the representations by accounting for the potential interplay between local chemical context and topological structure. Second, we combine Transformer with self-supervised contrastive learning (SSCL) to learn representations for targets by modelling protein amino acids sequences. The scheme allows to effectively preserve the intrinsic characteristics of the sequences. Finally, we introduce a bilinear attention network to obtain an integrated representation by adaptively incorporating drug and target representations. Benchmarking experiments on two datasets demonstrated that CSCL-DTI 1 outperforms six state-of-the-art methods.

关键词： Drugs Proteins Representation learning Protein engineering Adaptation models Contrastive learning Predictive models Transformers Amino acids Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Robust Optimization Under Decision Dependent Uncertainty

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1295-1306页

作者： Yunfan Zhang Feng Liu Yifan Su Yue Chen Zhaojian Wang João P.S.Catalão State Key Laboratory of Power System and Generation Equipment the Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Mechanical and Automation Engineering the Chinese University of Hong KongHong Kong SARChina Ministry of Education Key Laboratory of System Control and Information Processing the Department of AutomationShanghai Jiao Tong Universityand also with Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240China Faculty of Engineering of the University of Porto and Institute for Systems and Computer Engineering Technology and Science(INESC TEC)Porto 4200-465Portugal IEEE

In the conventional robust optimization(RO)context,the uncertainty is regarded as residing in a predetermined and fixed uncertainty *** many applications,however,uncertainties are affected by decisions,making the current RO framework *** paper investigates a class of two-stage RO problems that involve decision-dependent *** introduce a class of polyhedral uncertainty sets whose right-hand-side vector has a dependency on the here-and-now decisions and seek to derive the exact optimal wait-and-see decisions for the second-stage problem.A novel iterative algorithm based on the Benders dual decomposition is proposed where advanced optimality cuts and feasibility cuts are designed to incorporate the uncertainty-decision *** computational tractability,robust feasibility and optimality,and convergence performance of the proposed algorithm are guaranteed with theoretical *** motivating application examples that feature the decision-dependent uncertainties are ***,the proposed solution methodology is verified by conducting case studies on the pre-disaster highway investment problem.

关键词： Benders decomposition decision-dependent uncertainty endogenous uncertainty robust optimization(RO)

来源：评论

学校读者我要写书评

暂无评论

Exploring the Role of Edge Distribution in Graph Convolutional Networks

SSRN

引用

SSRN 2023年

作者： He, Liancheng Bai, Liang Yang, Xian Liang, Jiye Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education School of Computer and Information Technology Shanxi University Shanxi Taiyuan030006 China Institute of Intelligent Information Processing Shanxi University Shanxi Taiyuan030006 China Alliance Manchester Business School The University of Manchester Manchester United Kingdom

Graph Convolutional Networks (GCNs) have been found to show excellent performance in processing graph-structured data by learning node representations through the aggregation of information from neighbors. While most GCN models assume strong homophily in the networks they process, some models are able to handle heterophilous graphs as well. The performance of these models can often be influenced by the selection of neighbors that participate in the node representation learning process. In this paper, we investigate the role of neighbors in GCNs from the perspective of edge distribution through both theoretical and empirical analyses. Based on our findings, we propose a new GCN model, the Graph Convolution Network with Improved Edge Distribution (GCN-IED), which generates both direct edges and hidden edges. Direct edges are generated based on the similarity between local neighborhoods, while hidden edges are implemented by aggregating information from multi-hop neighbors. Extensive experiments were conducted on various graph benchmark datasets to evaluate the effectiveness of our proposed method. The results of these experiments demonstrate that GCN-IED performs better on heterophilous datasets than other state-of-the-art GCN methods. © 2023, 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

VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity Recognition 27

VANER: Leveraging Large Language Model for Versatile and Ada...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Bian, Junyi Zhai, Weiqi Huang, Xiaodi Zheng, Jiaxuan Zhu, Shanfeng School of Computer Science Fudan University Shanghai200433 China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China Ministry of Education Shanghai200433 China MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China Zhangjiang Fudan International Innovation Center Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai200433 China School of Computing and Mathematics Charles Sturt University AlburyNSW2640 Australia

ISBN: (纸本)9781643685489

The prevalent solution for BioNER involves using representation learning techniques combined with sequence ***, such methods are inherently task-specific, demonstrate poor generalizability, and often require a dedicated model for each *** leverage the versatile capabilities of recent large language models (LLMs), several approaches have explored generative techniques for entity ***, these approaches often fall short compared to previous sequence labeling *** this paper, we utilize the open-sourced LLM LLaMA2 as the backbone model, and design specific instructions to distinguish between different types of entities and *** combining the LLM's understanding of instructions with sequence labeling techniques, we train a model using a mix of datasets capable of extracting various types of *** that the backbone LLMs lacks specialized medical knowledge, we also integrate external entity knowledge bases and employ instruction tuning to enable the model to densely recognize curated *** parameter-efficient training model, VANER, significantly outperforms previous LLMs-based *** the first time, as an LLM-based model, VANER surpasses the majority of conventional state-of-the-art BioNER systems, achieving the highest F1 scores across three datasets. © 2024 The Authors.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Adaptive Latent Factor Analysis via Generalized Momentum-Incorporated Particle Swarm Optimization 19

Adaptive Latent Factor Analysis via Generalized Momentum-Inc...

引用

19th IEEE International Conference on Networking, Sensing and Control, ICNSC 2022

作者： Chen, Jiufang Yuan, Ye School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing400714 China Chongqing School University of Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9781665472432

Stochastic gradient descent (SGD) algorithm is an effective learning strategy to build a latent factor analysis (LFA) model on a high-dimensional and incomplete (HDI) matrix. A particle swarm optimization (PSO) algorithm is commonly adopted to make an SGD-based LFA model's hyper-parameters, i.e., learning rate and regularization coefficient, self-adaptation. However, a standard PSO algorithm may suffer from accuracy loss caused by premature convergence. To address this issue, this paper incorporates more historical information into each particle's evolutionary process for avoiding premature convergence following the principle of a generalized-momentum (GM) method, thereby innovatively achieving a novel GM-incorporated PSO (GM-PSO). With it, a GM-PSO-based LFA (GMPL) model is further achieved to implement efficient self-adaptation of hyper-parameters. The experimental results on three HDI matrices demonstrate that the GMPL model achieves a higher prediction accuracy for missing data estimation in industrial applications. © 2022 IEEE.

关键词： Momentum

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：