检索结果-内蒙古大学图书馆

International Conference on Distributed Computing Systems

作者： Shunbin Dong Yumin Xie Jin Zhao Kun Qiu School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

Network policy plays a crucial role in cloud-native networking, especially in multi-tenant scenarios. It provides precise control over connectivity by specifying source and destination endpoints, traffic types, and other criteria to allow or deny traffic. However, manual configuration of these policies introduces the risk of errors, leading to isolation violations or network service unavailability. Therefore, network policy verification is essential for maintaining security and quality of service in cloud-native networking. Currently, a naïve approach involves individually checking each policy within the cluster, which can take over 100s for verification in a cluster size of over 100k. Existing verification frameworks, like Kano and Verikube, improve performance by leveraging pre-filtering and Satisfiability Modulo Theories (SMT) solvers, achieving a 3.12x to 12.99x performance boost over the naïve baseline. However, as network policy changes rapidly within 100ms in real cloud-native networks, both frameworks need over 10s to perform verification for cluster sizes over 100k, which is far from satisfying. To overcome these issues, we propose and implement a novel network policy verification framework NPV, which utilizes the policy-label pre-filter process with bitwise compression. We further enhance the policy verification algorithm with a policy-namespace divide-and-conquer strategy to improve the data-level parallelism. We implement NPV on commodity servers and evaluate its performance using real network policy datasets. Our experiments indicate that, compared with the state-of-the-art methods, NPV can achieve up to 139.00x to 651.06x improvement in verification time compared to Kano and Verikube, with 65% less memory usage.

关键词： Memory management Clustering algorithms Quality of service Manuals Parallel processing Servers Security

来源：评论

学校读者我要写书评

暂无评论

MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time

arXiv

引用

arXiv 2024年

作者： Zhang, Mozhi Wang, Pengyu Tan, Chenkun Huang, Mianqiu Zhang, Dong Zhou, Yaqian Qiu, Xipeng School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential. Existing alignment techniques, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), typically embed predefined preferences directly within the model’s parameters. These methods, however, often result in a static alignment that can not account for the diversity of human preferences in practical applications. In response to this challenge, we propose an effective method, MetaAlign, which aims to help LLMs dynamically align with various explicit or implicit preferences specified at inference time. Experimental results show that LLMs optimized on our meticulously constructed MetaAlign Dataset can effectively align with any preferences specified at the inference stage, validating the feasibility of MetaAlign. We hope that our work can provide some insights into the alignment of language models. 1 Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Attention-based Dual-Branch Network for Micro-Expression Recognition with Global-Local Feature Fusion

Attention-based Dual-Branch Network for Micro-Expression Rec...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Yupeng Qi Mayire Ibrayim Askar Hamdulla School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China

ISBN: (数字)9798350364132

ISBN: (纸本)9798350364149

Micro-expression(ME) is an uncontrollable muscle movement that appears on the face when people try to hide or inhibit their real emotions, which has the problems of short duration, small movement amplitude and uneven distribution. In order to solve the problem of localization and asymmetry in the distribution of ME features, this paper proposes a new two-branch attention network to recognize MEs, which utilizes the attention mechanism to capture global and local ME features. The network is mainly divided into three parts: data preprocessing, ME feature learning and feature fusion classification. First, the data preprocessing first extracts the ME optical flow features and then divides them into four regions, which are used as inputs to the two-branch network respectively. Second, the two-branch network uses the Inception-MSFE global multi-scale feature extraction network incorporating the attention mechanism (CBAM) and the Swin Transformer-based local feature extraction network for feature learning, respectively. Finally, MEs are predicted by fusing global and local features of MEs. Experimental validation is carried out on three datasets, CASME II, SAMM, and SMIC, which proves that Acc, UAR, and UF1 are 0.797, 0.702, and 0.698 on the SAMM dataset, respectively; Acc, UAR, and UF1 are 0.734, 0.723, and 0.729 on SMIC, respectively; and on the CASME II dataset, Acc, UAR and UF1 are 0.865, 0.872, and 0.889, respectively, which are competitive with other state-of-the-art methods.

关键词： Representation learning Attention mechanisms Computational modeling Data preprocessing Training data Feature extraction Generative adversarial networks Transformers Data mining Optical flow

来源：评论

学校读者我要写书评

暂无评论

An Exploration of Prompt-Based Zero-Shot Relation Extraction Method 21

An Exploration of Prompt-Based Zero-Shot Relation Extraction...

引用

21st China National Conference on Computational Linguistics, CCL 2022

作者： Zhao, Jun Hu, Yuan Xu, Nuo Gui, Tao Zhang, Qi Chen, Yunwen Gao, Xiang School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Co. Ltd. Shanghai China

ISBN: (纸本)9783031183140

Zero-shot relation extraction is an important method for dealing with the newly emerging relations in the real world which lacks labeled data. However, the mainstream two-tower zero-shot methods usually rely on large-scale and in-domain labeled data of predefined relations. In this work, we view zero-shot relation extraction as a semantic matching task optimized by prompt-tuning, which still maintains superior generalization performance when the labeled data of predefined relations are extremely scarce. To maximize the efficiency of data exploitation, instead of directly fine-tuning, we introduce a prompt-tuning technique to elicit the existing relational knowledge in pre-trained language model (PLMs). In addition, very few relation descriptions are exposed to the model during training, which we argue is the performance bottleneck of two-tower methods. To break through the bottleneck, we model the semantic interaction between relational instances and their descriptions directly during encoding. Experiment results on two academic datasets show that (1) our method outperforms the previous state-of-the-art method by a large margin with different samples of predefined relations;(2) this advantage will be further amplified in the low-resource scenario. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Construction of a Three-Layer Directed Network Model with Multimodal Characteristics

Construction of a Three-Layer Directed Network Model with Mu...

引用

2021 International Conference on Applied Mathematics, Modeling and computer Simulation, AMMCS 2021

作者： Zhang, Na Xiao, Yuzhi Zhao, Haixing Tang, Cunyang Cui, Baoyang College of Computer Qinghai Normal University Xining China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining810008 China

ISBN: (纸本)9781643682549

The multi-layer directed network model focuses on portraying the directionality, diversity and difference of the edges in the network. It is also one of the powerful tools for analyzing the complexity of the network system and the heterogeneous interaction characteristics between network layers. This paper constructs three three-layer directed network models combined with traditional complex network theory and analyzes their degree distribution characteristics. By controlling the out-degree and in-degree of the middle-level nodes, a network structure with multi-peak characteristics is configured. Combined with numerical simulation, it is concluded that the number of links between the layers of the directed network makes the network characterize the characteristics of unimodal, bimodal, and trimodal;the combination of the optimal mechanism and the changes in the number of inter-layer links, the network characteristics show the coexistence of power law and unimodal. The research results of this paper have practical value for the analysis of network generation mechanism and correlation law by using multi-layer directed network theory in the era of big data. © 2022 The authors and IOS Press.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

User Behavior-Based Collaborative Filtering Recommendation Algorithm and Visualization in Second-Hand Trading Platform 2

User Behavior-Based Collaborative Filtering Recommendation A...

引用

2nd IEEE International Conference on Sensors, Electronics and computer Engineering, ICSECE 2024

作者： Qiao, Rui Wang, Xin Zhong, Xiaoben School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan China Yunnan College of Business Management Anning650301 China

ISBN: (纸本)9798350373646

In the backdrop of the digital era, the demand for second-hand trading within campuses has seen a significant rise. This project aims at designing a second-hand trading platform that merges the latest technological trends, providing a secure and convenient trading environment for students. The system utilizes Spring Boot for backend development and Vue along with ElementUI for constructing the user interface, ensuring efficient operation and enhancing user interaction experience. The server employs Spring Boot's built-in Tomcat, simplifying the deployment process. For data persistence, Mybatis framework is used for flexible and efficient interactions with the MySQL database. The platform introduces a collaborative filtering algorithm based on user behavior for smart product recommendations, further improving the user experience. The system integrates core modules such as user management, product browsing, shopping cart functionalities, and order processing, innovatively introducing an offline transaction confirmation mechanism to ensure transaction security and reliability while avoiding legal risks associated with online payments. With its B/S architecture, the platform operates more smoothly, making it more accessible to users. Experimental results demonstrate that the platform has a user-friendly interface and efficient data processing capabilities, receiving widespread recognition and praise from users, proving its practicality and innovativeness. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Prediction of GDP Carbon Emission Based on Grey Model and Neural Network 4th

Prediction of GDP Carbon Emission Based on Grey Model and Ne...

引用

4th EAI International Conference on Robotic Sensor Networks, 2020

作者： Zhang, Feng Zhao, Huihuang Ramasamy, Manimaran College of Computer Science and Technology Hengyang Normal University Hengyang China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang China

ISBN: (纸本)9783030704506

In order to improve the prediction accuracy of Gross Domestic Product (GDP) carbon emission, combining the advantages of grey prediction and neural network, a discrete grey neural network prediction model named DGMBP is established. This model not only has the advantages of less data sample and larger development coefficient range of GM 1,1 model but also combines the advantages of neural network to deal with nonlinear data sample. Taking the GDP carbon emission data of China, India, the United States and the European Union as an example, the prediction results obtained are stable, and the accuracy of the prediction data is over 95%, which is much higher than that obtained by the linear regression equation and the logical regression equation. Finally, the carbon emission of GDP in 2020–2030 is predicted by using this model. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Embedding expert demonstrations into clustering buffer for effective deep reinforcement learning

引用

Frontiers of Information Technology & Electronic Engineering 2023年第11期24卷 1541-1556页

作者： Shihmin WANG Binqi ZHAO Zhengfeng ZHANG Junping ZHANG Jian PU Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China

As one of the most fundamental topics in reinforcement learning(RL),sample efficiency is essential to the deployment of deep RL *** most existing exploration methods that sample an action from different types of posterior distributions,we focus on the policy sampling process and propose an efficient selective sampling approach to improve sample efficiency by modeling the internal hierarchy of the ***,we first employ clustering methods in the policy sampling process to generate an action candidate *** we introduce a clustering buffer for modeling the internal hierarchy,which consists of on-policy data,off-policy data,and expert data to evaluate actions from the clusters in the action candidate set in the exploration *** this way,our approach is able to take advantage of the supervision information in the expert demonstration *** on six different continuous locomotion environments demonstrate superior reinforcement learning performance and faster convergence of selective *** particular,on the LGSVL task,our method can reduce the number of convergence steps by 46.7%and the convergence time by 28.5%.Furthermore,our code is open-source for *** code is available at https://***/Shihwin/SelectiveSampling.

关键词： Reinforcement learning Sample eficiency Sampling process Clustering methods Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

SAMNER: Image Screening and Cross-Modal Alignment Networks for Multimodal Named Entity Recognition

SAMNER: Image Screening and Cross-Modal Alignment Networks f...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Luyi Yang School of Computer Science and Technology Xinjiang University Xinjiang China Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

With the proliferation of social media data, Multimodal Named Entity Recognition (MNER) has received much attention; using different data modalities is crucial for the development of natural language processing and neural networks. However, existing methods suffer from two drawbacks: 1) text-image pairs in the data only sometimes correspond to each other, and it is impossible to rely on contextual information due to the short text nature of social media. 2) Despite the introduction of visual information, heterogeneity gaps may occur in previous complex fusion methods, leading to misidentification. This paper proposes a new synthetic image with a selected graphic alignment network(SAMNER) to address these challenges and construct a matching relationship between external images and text. To solve the graphic mismatch problem, we use a stable diffusion model to generate the images and perform entity labeling. Specifically, we generate images and perform entity labeling through the stable diffusion model to generate the image with the highest match to the text, filter the generated images by the internal image set to generate the best image, and then perform multimodal fusion to predict the entity labeling, we design a simple and effective multimodal attentional alignment mechanism to obtain a better visual representation, and we conduct a large number of experiments. The experiments prove that our model produces competitive results on the two publicly available datasets.

关键词： Visualization Matched filters Image recognition Social networking (online) Text recognition Neural networks Named entity recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-branch Network with Cross-Domain Feature Fusion for Anomalous Sound Detection 1

引用

18th National Conference on Man-Machine Speech Communication, NCMMSC 2023

作者： Fang, Wenjie Fan, Xin Hu, Ying School of Computer Science and Technology Xinjiang University Urumqi China Key Laboratory of signal detection and processing in Xinjiang Urumqi China

ISBN: (数字)9789819706013

ISBN: (纸本)9789819706006

Anomalous sound detection (ASD) is a key technology to identify abnormal sounds in various industries. Self-supervised anomalous sound detection aims at detecting unknown machine anomalous sounds by learning the characteristics of the normal sounds using metainformation. In this paper, we propose a multi-branch network with cross-domain feature fusion (MBN-CFF) for self-supervised ASD task. The multi-branch network splits the complete feature representations and feeds them individually into classifiers to generate category predictions. The weighted loss, calculated by multiple predictions and the real labels, guides the model training process. We also design a cross-domain feature fusion (CFF) block for effectively fusing the time-domain and frequency-domain features and an attentive sandglass (AS) block for effectively extracting features. Experimental results on the DCASE2020 challenge task 2 show that our MBN-CFF network achieves the best performance with the AUC score of 94.73% and pAUC score of 88.74%, respectively, compared to the other five existing methods for anomalous sound detection. The results of ablation experiments show the effectiveness of CFF and AS blocks, multi-brach prediction (MBP). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Anomaly detection

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：