检索结果-内蒙古大学图书馆

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

Few-Shot Open-Set Object Detection via Conditional Evidence Decoupling

arXiv

引用

arXiv 2024年

作者： Wu, Zhaowei Su, Binyi Zhang, Hua Zhou, Zhong The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300401 China The State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Zhongguancun Laboratory Beijing100190 China

Few-shot Open-set Object Detection (FOOD) poses a significant challenge in real-world scenarios. It aims to train an open-set detector under the condition of scarce training samples, which can detect known objects while rejecting unknowns. Under this challenging scenario, the decision boundaries of unknowns are difficult to learn and often ambiguous. To mitigate this issue, we develop a two-stage open-set object detection framework with prompt learning, which delves into conditional evidence decoupling for the unknown rejection. Specifically, we propose an Attribution-Gradient-based Pseudo-unknown Mining (AGPM) method to select region proposals with high uncertainty, which leverages the discrepancy in attribution gradients between known and unknown classes, alleviating the inadequate unknown distribution coverage of training data. Subsequently, we decouple known and unknown properties in pseudo-unknown samples to learn distinct knowledge with proposed Conditional Evidence Decoupling (CED), which enhances separability between knowns and unknowns. Additionally, we adjust the output probability distribution through Abnormal Distribution Calibration (ADC), which serves as a regularization term to establish robust decision boundaries for the unknown rejection. Our method has achieved superior performance over previous state-of-the-art approaches, improving the mean recall of unknown class by 7.24% across all shots in VOC10-5-5 dataset settings and 1.38% in VOC-COCO dataset settings. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Tracking Dialog States in Goal-Oriented Dialogues using a BERT-Based Siamese Network 27

Tracking Dialog States in Goal-Oriented Dialogues using a BE...

引用

27th International Conference on Knowledge Based and Intelligent Information and engineering Sytems, KES 2023

作者： Jbene, Mourad Tigani, Smail Chehri, Abdellah Chaibi, Hasna Saadane, Rachid Hassania School of Public Works Casablanca Morocco AAIR Lab Digital Engineering and Artificial Intelligence Systems High Private School Casablanca20250 Morocco Department of Mathematics and Computer Science Royal Military College KingstonON11 K7K 7B4 Canada SUPMTI Genius Laboratory Rabat Morocco

A dialogue state tracker is a component in a task-oriented dialogue system that monitors the current state of a conversation and gives information about its context and history to other system components. The dynamic and open-ended character of human interactions is one of the primary obstacles in dialogue state monitoring, necessitating robust and adaptable models to keep up with the quick context changes. Recently, numerous deep learning-based algorithms have been developed for this purpose. Still, these models are typically heavily-engineered and conceptually sophisticated, making them challenging to deploy, debug, and maintain in a production environment. To overcome these challenges, we offer the BERT-SIAM-DST model, a unique way to dialogue state monitoring employing a Siamese network with BERT as the base network. This model uses the robust representation capabilities of BERT and the ability of Siamese networks to record correlations between inputs to make accurate predictions regarding the current state of the discussion. In addition, the number of parameters does not increase proportionally with the size of the ontology, and the model is adaptable to alterations in the domain ontology. We test the performance of the BERT-SIAM-DST model on the standard WoZ 2.0 dataset of annotated dialogues and compare it to other approaches. Compared to numerous baseline models, the BERT-SIAM-DST model is effective at tracking the state of discussions, demonstrating the promise of BERT-based Siamese networks for this purpose. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Conversational systems Dialog management Dialog state tracking Task-Oriented Dialog systems Transformer-based models

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Multitasking Descriptor Optimization for Point Cloud Registration

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Wu, Yue Sheng, Jinlong Ding, Hangqi Gong, Peiran Li, Hao Gong, Maoguo Ma, Wenping Miao, Qiguang School of Computer Science and Technology Xidian University Xi’an China Key Laboratory of Collaborative Intelligence Systems Ministry of Education School of Electronic Engineering Xidian University Xi’an China Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education School of Artificial Intelligence Xidian University Xi’an China

Point cloud registration is an important task for other point cloud tasks. Feature-based methods are widely adopted for their speed and efficiency in point cloud registration. The descriptive capability of features extracted by a single geometric descriptor is limited. Descriptive capabilities can be improved by concatenating features extracted from multiple descriptors. However, due to the existence of redundant and irrelevant features, the correct corresponding points are difficult to match, which further affects the registration effect. We propose an evolutionary multitasking point cloud descriptor optimization method. Integrate existing descriptors to optimize descriptors with stronger description ability. Labeling features to calculate the feature importance for the registration and generating multitasks. In optimized processing, approximate evaluation which is calculated by prior correspondence saved in the database replaces the expensive searching correspondences process in the entire point cloud. Finally, a multiscale filter is developed to remove error correspondences by the geometric information from multiple scale descriptor features. Experimental demonstrate that the proposed approach can optimize a feature subset with higher descriptive capability compared to other methods and show superior point cloud registration performance on 14 point cloud models. This is the first paper on point cloud descriptor optimization, which provides a new idea for point cloud registration research. IEEE

关键词： Job analysis

来源：评论

学校读者我要写书评

暂无评论

Federated graph learning for cross-domain recommendation 24

Federated graph learning for cross-domain recommendation

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Ziqi Yang Zhaopeng Peng Zihui Wang Jianzhong Qi Chaochao Chen Weike Pan Chenglu Wen Cheng Wang Xiaoliang Fan Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University China and Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Computing and Information Systems The University of Melbourne Australia College of Computer Science and Technology Zhejiang University Hangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798331314385

Cross-domain recommendation (CDR) offers a promising solution to the data sparsity problem by enabling knowledge transfer between source and target domains. However, many recent CDR models overlook crucial issues such as privacy as well as the risk of negative transfer (which negatively impact model performance), especially in multi-domain settings. To address these challenges, we propose FedGCDR, a novel federated graph learning framework that securely and effectively leverages positive knowledge from multiple source domains. First, we design a positive knowledge transfer module that ensures privacy during inter-domain knowledge transmission. This module employs differential privacy-based knowledge extraction combined with a feature mapping mechanism, transforming source domain embeddings from federated graph attention networks into reliable domain knowledge. Second, we design a knowledge activation module to filter out potential harmful or conflicting knowledge from source domains, addressing the issues of negative transfer. This module enhances target domain training by expanding the graph of the target domain to generate reliable domain attentions and fine-tunes the target model for improved negative knowledge filtering and more accurate predictions. We conduct extensive experiments on 16 popular domains of the Amazon dataset, demonstrating that FedGCDR significantly outperforms state-of-the-art methods. We open source the code at https://***/LafinHana/FedGCDR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic Matching

arXiv

引用

arXiv 2024年

作者： Jena, Rohit Chaudhari, Pratik Gee, James C. Computer and Information Science University of Pennsylvania United States Electrical and Systems Engineering University of Pennsylvania United States Radiology Perelman School of Medicine University of Pennsylvania United States Penn Image Computing and Science Laboratory University of Pennsylvania United States

The paper proposes FireANTs, the first multi-scale Adaptive Riemannian Optimization algorithm for dense diffeomorphic image matching. One of the most critical and understudied aspects of diffeomorphic image matching algorithms are its highly ill-conditioned nature. We quantitatively capture the extent of ill-conditioning in a typical MRI matching task, motivating the need for an adaptive optimization algorithm for diffeomorphic matching. To this end, FireANTs generalizes the concept of momentum and adaptive estimates of the Hessian to mitigate this ill-conditioning in the non-Euclidean space of diffeomorphisms. Unlike common non-Euclidean manifolds, we also formalize considerations for multi-scale optimization of diffeomorphisms. Our rigorous mathematical results and operational contributions lead to a state-of-the-art dense matching algorithm that can be applied to generic image data with remarkable accuracy and robustness. We demonstrate consistent improvements in image matching performance across a spectrum of community-standard medical and biological correspondence matching challenges spanning a wide variety of image modalities, anatomies, resolutions, acquisition protocols, and preprocessing pipelines. This improvement is supplemented by from 300× up to 3200× speedup over existing state-of-the-art algorithms. For the first time, we perform diffeomorphic matching of sub-micron mouse cortex volumes at native resolution. Our fast implementation also enables hyperparameter studies that were intractable with existing correspondence matching algorithms. © 2024, CC BY.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Separating Content and Style for Unsupervised Image-to-Image Translation 32

Separating Content and Style for Unsupervised Image-to-Image...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Liu, Yunfei Wang, Haofei Yue, Yang Lu, Feng State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Beihang University Beijing China

Unsupervised image-to-image translation aims to learn the mapping between two visual domains with unpaired samples. Existing works focus on disentangling domain-invariant content code and domain-specific style code individually for multimodal purposes. However, less attention has been paid to interpreting and manipulating the translated image. In this paper, we propose to separate the content code and style code simultaneously in a unified framework. Based on the correlation between the latent features and the high-level domain-invariant tasks, the proposed framework demonstrates superior performance in multimodal translation, interpretability and manipulation of the translated image. Experimental results show that the proposed approach outperforms the existing unsupervised image translation methods in terms of visual quality and diversity. Code and data have been released at https://***/DreamtaleCore/SCS-UIT. © 2021. The copyright of this document resides with its authors.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Robust Event-Triggered Control of Nonlinear systems Under a Global Sector-Bound Condition

引用

Guidance, Navigation and Control 2022年第2期2卷 59-79页

作者： Pengpeng Zhang Tengfei Liu Zhong-Ping Jiang Department of Control Science&Engineering Frontiers Science Center for Intelligent Autonomous SystemsTongji UniversityShanghai 201804P.R.China State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819P.R.China Department of Electrical and Computer Engineering New York University370 Jay StreetBrooklynNY 11201USA

This paper studies an event-tniggered control problem for nonlinear systems subject to both external disturbancoes and dy namic *** is assumed that the system satisfies a global sector bound *** avold infnitely fast samplng,a novel eventriggred sampling mechanism is propoeed,which use8 not only the measuned system state but also an estimation of the inluence of the *** the propoeed design,the intersampling intervals an be lower bounded by a poeitive constant,and it is independent of botb external disturbances and dynamie ***,the doeedl loop event-tniggered system i proved to be input-torstate stable with repect to the extemal *** smalgain techmigues are;used for the stability analysis of the dloeeil-bop system.

关键词： Event-triggered control external disturbance dynamic uncertainty input-to-state stability

来源：评论

学校读者我要写书评

暂无评论

Taming "data-hungry" reinforcement learning? stability in continuous state-action spaces 24

Taming "data-hungry" reinforcement learning? stability in co...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Yaqi Duan Martin J. Wainwright Department of Technology Operations and Statistics Stern School of Business New York University New York NY Laboratory for Information and Decision Systems Statistics and Data Science Center and Department of Electrical Engineering and Computer Science and Department of Mathematics Massachusetts Institute of Technology Cambridge MA

ISBN: (纸本)9798331314385

We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights two key stability properties, relating to how changes in value functions and/or policies affect the Bellman operator and occupation measures. We argue that these properties are satisfied in many continuous state-action Markov decision processes. Our analysis also offers fresh perspectives on the roles of pessimism and optimism in off-line and on-line RL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Overall performance indicators for sustainability assessment and management in mining industry 7

Overall performance indicators for sustainability assessment...

引用

7th International Conference on Optimization and Applications, ICOA 2021

作者： Lamjahdi, Aicha Bouloiz, Hafida Gallab, Maryam Ibn Zohr University Laboratory of Systems Engineering and Decision-making Support National School of Applied Sciences Agadir Morocco ENSMR MIS - LISTD Laboratory Department of Computer Science Rabat Morocco

ISBN: (纸本)9781665441032

The mining industry is the source of the production of many consumer goods and equipment. Therefore, the companies that control this activity play a significant role in the global economy. However, it is an important source of pollution of water, air, soil and ecosystems by metals. It exploits fossil and non-renewable resources, requiring large amounts of energy and sometimes water. Thus, implementing a sustainable approach through an overall performance integration in manufacturing practices, is become a necessity in this sector. Hence, this research presents a collection of key performance indicators for overall performance evaluation and management in mining industry. The proposed indicators were established from literature on the basis of the sustainability triple bottom line of economic, social, and environmental factors. A survey is conducted then, in a Moroccan mining industry to validate the adaptability of the chosen indicators with the industry activities and practices. Future work will further develop an evaluation tool that will help managers to assess the overall performance in mining industry and to take the appropriate actions to increase its competitiveness. © 2021 IEEE.

关键词： Decision making

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：