检索结果-内蒙古大学图书馆

FedECCR: Federated Learning Method with Encoding Comparison and Classification Rectification 19th

FedECCR: Federated Learning Method with Encoding Comparison...

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yan Zheng, Hui Wang, Xin Zhang, Beibei Zhou, Mingyao Zhang, Jilin Ren, YongJian School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Zhejiang Lab Hangzhou311100 China Hangzhou Huawei Communication Technology Co. Ltd. Hangzhou310052 China

ISBN: (纸本)9783031545306

Federated learning is a distributed training method that integrates multi-party data information using privacy-preserving technologies through dispersed client data sets to jointly construct a global model under the coordination of a central server. However, in practical applications, there is a high degree of data distribution skewness among clients, which causes the optimization direction of the client models to diverge, resulting in model bias and reducing the accuracy of the global model. Existing methods require the calculation and transmission of much information to correct the optimization direction of the client models, or only roughly limit the deviation of the client models end-to-end, ignoring targeted processing of the internal structure of the model, resulting in unclear improvement effects. To address these problems, we propose a federated optimization algorithm FedECCR based on encoding contrast and classification correction. This algorithm divides the model into an encoder and a classifier. It utilizes prototype contrastive training of the model encoder and unbiased classification correction of the classifier. This approach notably improves the accuracy of the global model while maintaining low communication costs. We conducted experiments on multiple data sets to evaluate the validity of our method, and the quantified results showed that FedECCR can improve the global model classification accuracy by approximately 1% to 6% compared to FedAvg, FedProx, and MOON. © ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering

Prompting Large Language Models with Answer Heuristics for K...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhenwei Shao Zhou Yu Meng Wang Jun Yu Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University China School of Computer Science and Information Engineering Hefei University of Technology China

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have sought to use a large language model (i.e., GPT-3 [3]) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of GPT-3 as the provided input information is insufficient. In this paper, we present Prophet-a conceptually simple framework designed to $prompt$ GPT-3 with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the model: answer candidates and answer-aware examples. Finally, the two types of answer heuristics are encoded into the prompts to enable GPT-3 to better comprehend the task thus enhancing its capacity. Prophet significantly outperforms all existing state-of-the-art methods on two challenging knowledge-based VQA datasets, OK-VQA and A-OKVQA, delivering 61.1% and 55.7% accuracies on their testing sets, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedAG:A Federated Learning Method Based on Data Importance Weighted Aggregation

FedAG:A Federated Learning Method Based on Data Importance W...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Xu, Mengchu Zeng, Yan Xue, Meiting Zhang, Ji-Lin Wan, Jian Zhou, Mingyao Wen, Yilin Shi, Yukun Hangzhou Dianzi University School of Computer Science and Technology Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China Zhejiang Engineering Research Center of Data Security Governance Hangzhou China Hangzhou Dianzi University School of Cyberspace Hangzhou China Huawei Enterprise Communication Technology Co Hangzhou China

ISBN: (纸本)9798350345384

Federated learning is a distributed machine learning approach that trains models with multiple clients and data locally. However, the existing methods ignore the differences between local models caused by the data heterogeneity, and give a high aggregation weight for the low-quality local model, which leads to low accuracy of the global model. For this problem, we propose a federated learning method based on data importance weighted aggregation, FedAG. It constructs an evaluation model of data importance based on the data distribution skewness, data volume, and data quality of clients, and aggregates local models with different weights computed by the evaluation model of data importance into a global model. We make experiments on five datasets including EMNIST, MNIST, and CIFAR-10. The results show that the accuracy of FedAG is respectively improved by 6.5%, 1.8%, 1.3% and 2.1%, compared with FedAvg, FedProx, FedVar, and Scaffold algorithms. © 2023 IEEE.

关键词： Scaffolds

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Interest Representation Network for Click-Through Rate Prediction

Evolutionary Interest Representation Network for Click-Throu...

引用

IEEE International Conference on Web Services (ICWS)

作者： Renjie Zhou Zhenming Jin Jian Wan Jilin Zhang Xingyu Guo Qiang Liu Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education ITMO Joint Institute Hangzhou Dianzi University Hangzhou China School of Information and Electronic Engineering Zhejiang University of Science and Technology Hangzhou China Dept. of Computer and Information Technology Zhejiang Police College Hangzhou China

The rapid development of the Internet has revo-lutionized our lives, providing us with an array of convenient services. However, this revolution has also led to the problem of data overload. Personalized recommendation services have been widely recognized as an effective solution to this problem by both the industrial and academic communities. Accurate prediction of click-through rate (CTR) is a critical task in personalized recommendation systems since it can improve the user’s shopping experience, ultimately increasing revenue for the platform. To achieve accurate CTR prediction, it is crucial to capture user interests. While several methods for interest modeling exist, challenges related to user interest evolution and user behavior noise need further attention. This paper proposes a novel CTR prediction model named the Evolutionary Interest Representation Network (EIRN), which learns the evolving interest representation of users from their behaviors, profiles, and environmental attributes. In the model, we introduce an advertisement correlation graph decomposition layer and a noise filter layer to enhance and purify the user behavior representation. An interest extraction layer is designed to capture sequential correlations and common characteristics between user behaviors, representing their interests. Additionally, as user interests evolve over time and their importance changes, an attention-based interest evolution layer is designed to track the evolution of user interests. Our proposed method is validated using four public datasets and an industrial dataset, showing its superiority over existing CTR prediction methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi2human: Controllable Human Image Generation with Multimodal Controls

SSRN

引用

SSRN 2023年

作者： Gu, Xiaoling Xu, Shengwenzhuo Wong, Yongkang Wu, Zizhao Yu, Jun Fan, Jianping Kankanhalli, Mohan S. Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University China National University of Singapore Singapore School of Digital Media Technology Hangzhou Dianzi University China

Generating high-quality and diverse human images presents a substantial difficulty within the field of computer vision, especially in developing controllable generative models that can utilize input from various modalities. Such models could enable innovative applications like digital human, fashion design, and content creation. In this study, we introduce Multi2Human, a two-stage image synthesis framework for controllable human image generation with multimodal controls. In the first stage, a novel WAvelet-vqVaE (WAVE) architecture is designed to embed human images using a learnable codebook. The WAVE model enhances the conventional Vector Quantized Variational Autoencoder (VQVAE) by integrating wavelets throughout the encoder, thereby enhancing the quality of image reconstruction and synthesis. In the second stage, a new Multimodal Conditioned Diffusion Model (MCDM) is de- signed to estimate the underlying prior distribution within the discrete latent space using a discrete diffusion process, thus allowing for human image generation condi- tioned on multimodal controls. Quantitative and qualitative analysis demonstrates that the proposed method has the ability to create high-quality, lifelike full-body human images while satisfying the specified multimodal controls. Our code is available at https://***/gxl-groups/Multi2Human. © 2023, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering

arXiv

引用

arXiv 2023年

作者： Yu, Zhou Ouyang, Xuecheng Shao, Zhenwei Wang, Meng Yu, Jun The Key Laboratory of Complex Systems Modeling and Simulation the School of Computer Science Hangzhou Dianzi University China The HDU-ITMO Joint Institute Hangzhou Dianzi University China The School of Computer Science and Information Engineering Hefei University of Technology China

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have resorted to using a powerful large language model (LLM) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of the blind LLM as the provided textual input is insufficient to depict the required visual information to answer the question. In this paper, we present Prophet—a conceptually simple, flexible, and general framework designed to prompt LLM with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the VQA model: answer candidates and answer-aware examples. Finally, the two types of answer heuristics are jointly encoded into a formatted prompt to facilitate the LLM’s understanding of both the image and question, thus generating a more accurate answer. By incorporating the state-of-the-art LLM GPT-3 [1], Prophet significantly outperforms existing state-of-the-art methods on four challenging knowledge-based VQA datasets. To demonstrate the generality of our approach, we instantiate Prophet with the combinations of different VQA models (i.e., both discriminative and generative ones) and different LLMs (i.e., both commercial and open-source ones). © 2023, CC BY.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

An Anomaly Detection Method Based on Adaptive Log and Dual Feature Fusion Analysis for Distributed systems

An Anomaly Detection Method Based on Adaptive Log and Dual F...

引用

Information systems and Computing Technology (ISCTech), International Conference on

作者： Yijiang Jia Kefei Li Ping Lu Baodi Xie Huayang Wang Jincai Chen School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China National Key Laboratory of Modeling and Simulation for Complex Systems Beijing China

In this study, we present a middleware-based approach for detecting anomalies in distributed systems. Our method facilitates the dynamic collection of logs at various levels of detail and incorporates an a priori dictionary-based compression strategy to process and transmit logs, minimizing the performance impact on distributed systems. Additionally, we utilize a dual feature fusion technique to analyze the logs. We evaluate the effectiveness of our approach by performing anomaly detection in a publish/subscribe distributed system and comparing it with existing methods. The results illustrate that our method outperforms other approaches, demonstrating superior performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm 29

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

29th IEEE International Conference on Parallel and Distributed systems, ICPADS 2023

作者： Zeng, Yan Huang, Chengchuang Ni, Yijie Zhou, Chunbao Zhang, Jilin Wang, Jue Zhou, Mingyao Xue, Meiting Zhang, Yunquan Hangzhou Dianzi University School of Computer Science and Technology Hangzhou310018 China Ministry of Education Key Laboratory for Modeling and Simulation of Complex Systems Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Hangzhou Dianzi University School of ITMO Joint Institute Hangzhou310018 China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing100086 China HuaWei China Institute of Computing Technology of the Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100086 China

ISBN: (纸本)9798350330717

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network's dataflow graph and device cluster's topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method. © 2023 IEEE.

关键词： Auto-Parallel Distributed machine learning Genetic algorithm Integer linear programming Model parallelism

来源：评论

学校读者我要写书评

暂无评论

Discovering API Directives from API Specifications with Text Classification

引用

Journal of computer Science & Technology 2021年第4期36卷 922-943页

作者： Jing-Xuan Zhang Chuan-Qi Tao Zhi-Qiu Huang Xin Chen College of Compute Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 210016China Key Laboratory of Safety-Critical Software(Nanjing University of Aeronautics and Astronautics) Ministry of Industry and Information TechnologyNanjing 210016China Key Laboratory of Complex Systems Modeling and Simulation(Hangzhou Dianzi University) Ministry of Education Hangzhou 310018China School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou 310018China

Application programming interface(API)libraries are extensively used by *** correctly program with APIs and avoid bugs,developers shall pay attention to API directives,which illustrate the constraints of ***,API directives usually have diverse morphologies,making it time-consuming and error-prone for developers to discover all the relevant API *** this paper,we propose an approach leveraging text classification to discover API directives from API ***,given a set of training sentences in API specifications,our approach first characterizes each sentence by three groups of ***,to deal with the unequal distribution between API directives and non-directives,our approach employs an under-sampling strategy to split the imbalanced training set into several subsets and trains several *** a new sentence in an API specification,our approach synthesizes the trained classifiers to predict whether it is an API *** have evaluated our approach over a publicly available annotated API directive *** experimental results reveal that our approach achieves an F-measure value of up to 82.08%.In addition,our approach statistically outperforms the state-of-the-art approach by up to 29.67%in terms of F-measure.

关键词： Application programming interface(API)directive API specification imbalanced learning text classification

来源：评论

学校读者我要写书评

暂无评论

Decentralized Event-Triggered Online Learning for Safe Consensus of Multi-Agent systems with Gaussian Process Regression

arXiv

引用

arXiv 2024年

作者： Dai, Xiaobing Yang, Zewen Xu, Mengtian Liu, Fangzhou Hattab, Georges Hirche, Sandra TUM School of Computation Information and Technology Technical University of Munich Munich80333 Germany Robert Koch Institute Berlin Germany National Key Laboratory of Modeling and Simulation for Complex Systems Harbin Institute of Technology 150001 China Department of Mathematics and Computer Science Freie Universität Berlin Berlin Germany

Consensus control in multi-agent systems has received significant attention and practical implementation across various domains. However, managing consensus control under unknown dynamics remains a significant challenge for control design due to system uncertainties and environmental disturbances. This paper presents a novel learning-based distributed control law, augmented by an auxiliary dynamics. Gaussian processes are harnessed to compensate for the unknown components of the multi-agent system. For continuous enhancement in predictive performance of Gaussian process model, a data-efficient online learning strategy with a decentralized event-triggered mechanism is proposed. Furthermore, the control performance of the proposed approach is ensured via the Lyapunov theory, based on a probabilistic guarantee for prediction error bounds. To demonstrate the efficacy of the proposed learning-based controller, a comparative analysis is conducted, contrasting it with both conventional distributed control laws and offline learning methodologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Multi agent systems

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：