检索结果-内蒙古大学图书馆

LBFL: A Lightweight Blockchain-based Federated Learning Framework with Proof-of-Contribution Committee Consensus

IEEE Transactions on Big data 2024年

作者： Qiao, Shaojie Jiang, Yuhe Han, Nan Hua, Wei Lin, Yufeng Min, Shengjie Wu, Xindong Chengdu University of Information Technology School of Software Engineering Chengdu610225 China Sichuan University NMPA Key Laboratory of Human Cosmetic Evaluation and Big Data West China Hospital Chengdu610041 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Hefei230009 China

Blockchain technology makes it possible to design robust decentralized federated learning (FL). Minimizing the communication cost and storage consumption incurred is one of the essential challenges. In addition, maintaining the security and privacy of Big data raises to be a difficult problem. Aiming to tackle these challenges, this paper presents LBFL (a Lightweight Blockchain-based FL framework) that offers three novel features. First, it employs a new committee consensus mechanism called Proof-of-Contribution, which is used to avoid the selection latency from the competition of miners and alleviate the congestion in cross-validation of parameters in an asynchronous fashion. Second, LBFL employs a role-adaptive incentive mechanism to estimate devices' workloads and identify malicious nodes effectively. Third, to cope with the excessive storage overheads incurred in full-replication, LBFL applies a new storage partition mechanism that distributes triple redundant chunks in ReedSolomon coding (RSC) evenly to participating devices with high fault tolerance and recovery efficiency. To evaluate LBFL, empirical studies are performed on the famous MNIST dataset and LBFL is compared with the state-of-the-art FL frameworks. The results demonstrate that LBFL can reduce evaluation latency and storage consumption by 69.2% and 72.1%, respectively, and the learning efficiency of LBFL is higher than the state-ofthe-art methods. In particular, important findings are obtained: the proposed role-adaptive incentive mechanism can properly identify malicious devices and switch the roles of legitimate devices to achieve good decentralization © 2015 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Zero-shot Learning Method with a Multi-Modal knowledge Graph

A Zero-shot Learning Method with a Multi-Modal Knowledge Gra...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Yuhong Zhang Haitao Shu Chenyang Bu Xuegang Hu Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Zero-shot learning aims to recognize unseen-classes using some seen-class samples as training set. It is challenging owing to that the feature representations of unseen-class samples are unavailable. Existing methods transfer the mapping from seen-classes to unseen-classes with the correlation as a bridge, in which, the semantic representations are used to discriminate the classes. However, the unavailability of visual representations for unseen-classes and the insufficient discrimination of semantic representations make the zero-shot learning challenging. Therefore, the visual representations are learned as complements to semantic representations to construct a multi-modal knowledge graph (KG), and a zero-shot learning method based on multi-modal KG is proposed in this paper. Specially, a semantic KG is introduced to capture the correlation of classes, and with the correlation, the visual feature representations of all classes are learned. Then, the discriminative visual representations and the semantic representations are used together to construct a multi-modal KG. With the multi-modal KG, the classifier for seen-classes is transferred to unseen classes. Extensive experimental results show the effectiveness of our method.

关键词： Learning systems Representation learning Training Bridges Visualization Correlation Semantics

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Cross-Domain Feature Representation Learning Method Based on Dual Constraints

Nonlinear Cross-Domain Feature Representation Learning Metho...

引用

IEEE International Conference on Big knowledge (ICBK)

作者： Han Ding Yuhong Zhang Shuai Yang Yaojin Lin Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Data Science and Intelligence Application Fujian Province University Zhangzhou China

Feature representation learning is a research focus in domain adaptation. Recently, due to the fast training speed, the marginalized Denoising Autoencoder (mDA) as a standing deep learning model has been widely utilized for feature representation learning. However, the training of mDA suffers from the lack of nonlinear relationship and does not explicitly consider the distribution discrepancy between domains. To address these problems, this paper proposes a novel method for feature representation learning, namely Nonlinear cross-domain Feature learning based Dual Constraints (NFDC), which consists of kernelization and dual constraints. Firstly, we introduce kernelization to effectively extract nonlinear relationship in feature representation learning. Secondly, we design dual constraints including Maximum Mean Discrepancy (MMD) and Manifold Regularization (MR) in order to minimize distribution discrepancy during the training process. Experimental results show that our approach is superior to several state-of-the-art methods in domain adaptation tasks.

关键词： Noise reduction Manifolds Training Adaptation models Kernel Deep learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-lingual acquisition on multimodal pre-training for cross-modal retrieval 22

Multi-lingual acquisition on multimodal pre-training for cro...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Liang Zhang Anwen Hu Qin Jin School of Information Renmin University of China School of Information Renmin University of China and Key Laboratory of Data Engineering and Knowledge Engineering (MOE) Renmin University of China

ISBN: (纸本)9781713871088

Vision and diverse languages are important information sources in our living world. A model that understands multi-modalities and multi-languages can be applied to a wider range of real-life scenarios. To build such a multimodal and multilingual model, existing works try to ensemble vision-language data from multiple languages in pre-training. However, due to the large number of languages, these works often require huge computing resources and cannot be flexibly extended to new languages. In this work, we propose a Multi-Lingual Acquisition (MLA) framework that can easily empower a monolingual Vision-Language Pre-training (VLP) model with multilingual capability. Specifically, we design a lightweight language acquisition encoder based on state-of-the-art monolingual VLP models. We further propose a two-stage training strategy to optimize the language acquisition encoder, namely the Native Language Transfer stage and the Language Exposure stage. With much less multilingual training data and computing resources, our model achieves state-of-the-art performance on multilingual image-text and video-text retrieval benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantifying Interactions between Layers in Duplex Networks Using Interactive Entropy

引用

Journal of Library & Information Studies 2020年第2期18卷 31-41页

作者： Zhang, Ronda J. Ye, Fred Y. International Joint Informatics Laboratory (IJIL) Nanjing University - University of Illinois Nanjing-Champaign Nanjing China Jiangsu Key Laboratory of Data Engineering and Knowledge Service School of Information Management Nanjing University Nanjing China

The multiplex network has attracted wide attention because it can better describe the various relationships in the real world, and the duplex network is a special two-layer form of it. The purpose of this research focuses on introducing new entropy-based measures for multiplex network, especially duplex network. The new measure called Interactive entropy in duplex network (IE) is based on information entropy, a key concept of information theory. It can be applied to various types of multiplex networks to quantify the differences between the layers of inside duplex network. [ABSTRACT FROM AUTHOR]

关键词： Duplex Network Interactive Entropy Multiplex Network

来源：评论

学校读者我要写书评

暂无评论

Extracting Feature and Opinion Words Effectively from Chinese Product Reviews

Extracting Feature and Opinion Words Effectively from Chines...

引用

International Conference on Fuzzy Systems and knowledge Discovery (FSKD)

作者： Wei Wei Hongyan Liu Jun He Hui Yang Xiaoyong Du Information School Renmin University of China China School of Economics and Management Tsinghua University China Key Laboratory of Data Engineering and Knowledge Engineering MOE China

Nowadays more and more people like to publish their comments on a product on the Web. Mining such unstructured data (product reviews) is exciting hot and challenging research and application topic. In this paper, we focus on mining product reviews written in Chinese. We aim at extract the structural information from Chinese product reviews. By structural information, we mean product features and corresponding opinion words expressed in each review text. There are already some works done for reviews written in English, but less in Chinese. In this paper, we propose an effective method to extract candidate features and some effective pruning rules to prune the features. Also, we introduce a pattern extraction and matching step to improve our results. The experiment results show our approach is very effective, and has a good recall and precision.

关键词： Feature extraction data mining Negative feedback Information retrieval Fuzzy systems Conference management knowledge management engineering management Helium Laboratories

来源：评论

学校读者我要写书评

暂无评论

Creating Something From Nothing: Unsupervised knowledge Distillation for Cross-Modal Hashing

Creating Something From Nothing: Unsupervised Knowledge Dist...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hengtong Hu Lingxi Xie Richang Hong Qi Tian School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Huawei Inc.

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

In recent years, cross-modal hashing (CMH) has attracted increasing attentions, mainly because its potential ability of mapping contents from different modalities, especially in vision and language, into the same space, so that it becomes efficient in cross-modal data retrieval. There are two main frameworks for CMH, differing from each other in whether semantic supervision is required. Compared to the unsupervised methods, the supervised methods often enjoy more accurate results, but require much heavier labors in data annotation. In this paper, we propose a novel approach that enables guiding a supervised method using outputs produced by an unsupervised method. Specifically, we make use of teacher-student optimization for propagating knowledge. Experiments are performed on two popular CMH benchmarks, i.e., the MIRFlickr and NUS-WIDE datasets. Our approach outperforms all existing unsupervised methods by a large margin.

关键词： Training Semantics Computational modeling Feature extraction Dogs Training data Task analysis

来源：评论

学校读者我要写书评

暂无评论

SGSH: Stimulate Large Language Models with Skeleton Heuristics for knowledge Base Question Generation

arXiv

引用

arXiv 2024年

作者： Guo, Shasha Liao, Lizi Zhang, Jing Wang, Yanling Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education China Singapore Management University Singapore Zhongguancun Laboratory China

knowledge base question generation (KBQG) aims to generate natural language questions from a set of triplet facts extracted from KB. Existing methods have significantly boosted the performance of KBQG via pre-trained language models (PLMs) thanks to the richly endowed semantic knowledge. With the advance of pre-training techniques, large language models (LLMs) (e.g., GPT-3.5) undoubtedly possess much more semantic knowledge. Therefore, how to effectively organize and exploit the abundant knowledge for KBQG becomes the focus of our study. In this work, we propose SGSH — a simple and effective framework to Stimulate GPT-3.5 with Skeleton Heuristics to enhance KBQG. The framework incorporates "skeleton heuristics", which provides more fine-grained guidance associated with each input to stimulate LLMs to generate optimal questions, encompassing essential elements like the question phrase and the auxiliary verb. More specifically, we devise an automatic data construction strategy leveraging ChatGPT to construct a skeleton training dataset, based on which we employ a soft prompting approach to train a BART model dedicated to generating the skeleton associated with each input. Subsequently, skeleton heuristics are encoded into the prompt to incentivize GPT-3.5 to generate desired questions. Extensive experiments demonstrate that SGSH derives the new state-of-the-art performance on the KBQG tasks. The code is now available on Github1 Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Generalized Unique Game Problem

Generalized Unique Game Problem

引用

2012年全国理论计算机科学学术年会(NCTCS2012)

作者： Peng Cui Key Laboratory of Data Engineering and Knowledge Engineering MOE School of Information Resource Management Renmin University of China Beijing 100872 P.R.China

this paper,the author defines Generalized Unique Game Problem (GUGP),where weights of the edges are allowed to be *** special types of GUGP are illuminated,GUGP-NWA,where the weights of all edges are negative,and GUGP-PWT(ρ),where the total weight of all edges are positive and the negative-positive ratio is at most ρ.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Xinzheng Li Yuhong Zhang Peipei Li Xuegang Hu Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Cross-network node classification aims to use a labeled source network to classify nodes in an unlabeled target network. Most of the existing cross-network node classification methods learn the network representations by capturing the node neighborhood and train the classifier on these representations. The performance is highly dependent on the high-quality neighborhood in the network. However, in applications, the degree of nodes generally follows a long-tail distribution, i.e., a significant proportion of nodes are tail nodes with sparse neighborhood. It poses a challenge to existing methods. To this end, a structure similarity graph for cross-network node classitication method (SCNC) is proposed in this paper. Firstly, the potential links between nodes are predicted with the structural similarity metric to construct structure similarity graph, which can enrich the neighborhood of tail nodes. Then, the embedding representations of the structural similarity graph are learned to capture more neighborhood information. Finally, the adversarial is used to learn the domain invariant representations to address cross-network divergence. Extensive experimental results show that our SCNC outperforms the state-of-the-art methods.

关键词： Network topology Tail Learning (artificial intelligence) Prediction algorithms Classification algorithms Noise measurement Task analysis

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：