检索结果-内蒙古大学图书馆

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Meilin Cao Jiqiong Jiang Jing Zhang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Research Center of Intelligent Computing Software Zhejiang Lab Hangzhou China

Achieving high-accuracy relation extraction usually requires a large well-annotated corpus for model training, which is extremely time-consuming and lab.r-intensive. Consequently, distant supervision, implemented as a multi-instance learning paradigm, was proposed to build models from bags using automated lab.led corpora, where massive noises are unavoidably introduced in the bag lab.ls, deteriorating the model performance. To deal with the above problem, this paper proposes novel multi-instance active learning for relation extraction, which aims to improve the classification performance of the learned models under the premise of using as few lab.led training samples as possible. The proposed active learning strategies for bag selection are based on the similarity between bags, the improved Fisher matrix, and the combination of the two (hybrid), respectively. Extensive experiment results on two real-world datasets under three base learners consistently show that our proposed active learning methods archive better performance for relation extraction, compared with three baseline methods. Furthermore, the hybrid bag selection strategy performs the best.

关键词： Training Learning systems

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features 38

Not All Diffusion Model Activations Have Been Evaluated as D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is availab.e at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficient Crowdsourcing for Video Analytics 40

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficien...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Chen, Yu Zhang, Sheng Zhou, Ziying Wang, Xiaokun Liang, Yu Chen, Ning Yan, Yuting Xiao, Mingjun Wu, Jie Qian, Zhuzhong Xu, Harry Nanjing University State Key Lab. for Novel Software Technology China School of Systems Science Beijing Normal University China School of Computer and Electronic Information School of Artificial Intelligence Nanjing Normal University China School of Computer Science and Technology University of Science and Technology of China China Temple University Center for Networked Computing United States Samueli School of Engineering University of California Computer Science Department Los Angeles United States

ISBN: (纸本)9798350317152

In recent years, many crowdsourcing platforms have emerged, using the resources of recruited workers to perform diverse outsourcing tasks, where the video analytics attracts much attention due to its practical implications. For maximum profits, platforms carefully choose the workers and determine the video analytics configurations to ensure accuracy;meanwhile, workers possess the flexibility to tailor the configurations for their indivi-dual gains, which makes it hard for platforms to optimize their profits considering the platform-worker conflicts. In this paper, we design an incentive mechanism for Multi-leader game-based video Analytics upon CROwdsourcing, named MACRO, to over-come the above situation. Under that mechanism, we first formu-late the utility optimization problems for platforms and workers, respectively. We then propose a dual ascent-based method to op-timally determine the video analytics configurations for a multi-platform game, ensuring Pareto efficiency. Moreover, in the context of a multi-leader game involving platform-worker conflicts, we design an incentive function with its incentive factor update strategy and propose an ADMM-based approach for maximizing incentives that motivate workers to contribute to the platforms' profits. Rigorous proofs demonstrate the linear convergence of the MACRO to the multi-leader Stackelberg equilibrium. Trace-driven experiments show that MACRO improves the Pareto efficiency by 26.3%, outperforming other approaches. © 2024 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

GLoT: A Novel Gated-Logarithmic Transformer for Efficient Sign Language Translation

GLoT: A Novel Gated-Logarithmic Transformer for Efficient Si...

引用

IEEE Future Networks World Forum (FNWF)

作者： Nada Shahin Leila Ismail Department of Computer Science and Software Engineering Intelligent Distributed Computing and Systems (INDUCE) Lab College of Information Technology UAE University Al-Ain United Arab Emirates Emirates Center for Mobility Research UAE University Al-Ain United Arab Emirates

ISBN: (数字)9798350379495

ISBN: (纸本)9798350379501

Machine Translation has played a critical role in reducing language barriers, but its adaptation for Sign Language Machine Translation (SLMT) has been less explored. Existing works on SLMT mostly use the Transformer neural network which exhibits low performance due to the dynamic nature of the sign language. In this paper, we propose a novel Gated-Logarithmic Transformer (GLoT) that captures the long-term temporal dependencies of the sign language as a time-series data. We perform a comprehensive evaluation of GloT with the transformer and transformer-fusion models as a baseline, for Sign-to-Gloss-to-Text translation. Our results demonstrate that GLoT consistently outperforms the other models across all metrics. These findings underscore its potential to address the communication challenges faced by the Deaf and Hard of Hearing community.

关键词： Sign language Adaptation models Translation Accuracy Terminology Neural networks Semantics Logic gates Transformers Testing

来源：评论

学校读者我要写书评

暂无评论

Learning from Crowds with Mutual Correction-Based Co-Training

Learning from Crowds with Mutual Correction-Based Co-Trainin...

引用

IEEE International Conference on Big Knowledge (ICBK)

作者： Nianshang Tian Ming Wu Jiqiong Jiang Jing Zhang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Zhejiang Lab Research Center of Intelligent Computing Software Hangzhou China

Collecting lab.ls from crowds is a feasible solution for large knowledge graph creation. However, errors in crowd-sourced lab.ls damage the predictive model training. Although various methods have been developed to correct noisy lab.ls, these traditional methods on the one hand do not take full advantage of the information from crowdsourced lab.ls, and on the other hand do not perform well facing complicated annotation conditions, especially when some crowd workers make highly correlated mistakes. To address this issue, this paper proposes a novel learning from crowds method, which can simultaneously correct lab.l noises and learn predictive models. The proposed method trains two data classifiers and a crowd aggregator. Each data classifier divides crowdsourced lab.led data into a clean set and a noisy set and predicts the lab.ls of the instances with a large loss in the noisy set. These instances are removed from the noisy set and put into the clean set. Then, the loss of the classifier is updated using the new clean and noisy sets. The data classifier with smaller loss is selected and trained with the crowd aggregator by maximizing their mutual information. Simultaneously, the smaller loss is back propagated to the other data classifier for training it. Experimental results on both synthetic and real-world datasets consistently show that the proposed method significantly outperforms the state-of-the-art methods in noise correction and predictive model learning.

关键词： Training Crowdsourcing Annotations Predictive models Propagation losses Data models Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Hybrid Parallel Inference for Large Model on Heterogeneous Clusters for High Throughput

Hybrid Parallel Inference for Large Model on Heterogeneous C...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Chaonong Xu Weiming Kong Min Liu Mingming Zhang Chao Li Luqi Gong Beijing Key Lab of Petroleum Data Mining China University of Petroleum (Beijing) Beijing China Institute of Intelligent Computing Zhejiang Lab Hangzhou China School of Computer Science (National Pilot Software Engineering School) BUPT Beijing China

In high-throughput intelligent computing scenarios, multi-device parallelism strategies based on data parallelism or pipeline parallelism have been extensively utilized to accelerate large deep neural network model inference. Data parallelism offers nearly linear improvement in inference speed, but it is limited by the memory capacity of a single device which constrains the model size. On the other hand, pipeline parallelism can support larger models, but the total communication of the activations among devices is high, which limits the improvement of the inference speed. To address the demand for efficient model inference in high-throughput heterogeneous scenarios, we proposes a hybrid parallelism strategy that combines data parallelism and pipeline parallelism. The strategy involves grouping heterogeneous device clusters and then employing inter-group data parallelism along with intra-group pipeline parallelism. Moreover, we propose an algorithm to find an optimal hybrid parallel inference strategy with maximum throughput. The control variables of the strategy includes the number of groups, group-device assignments and model partition ratios. Our experimental evaluation demonstrates that compared to PipeEdge, a pipeline parallel inference framework for heterogeneous cluster, our strategy can achieve 1.7× −3.4× acceleration in an 8-device heterogeneous cluster without loss of accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time Series Fusion Model for Predicting Electric power tools and equipment

Time Series Fusion Model for Predicting Electric power tools...

引用

Robotics, intelligent Control and Artificial Intelligence (RICAI), International Conference on

作者： Liang Xue Xinghong Ling Lei Yang Yang Yang Computing Science and Artificial Intelligence College Suzhou City University Suzhou China College of Computer Science and Software Engineering Hohai University Nanjing China Suzhou Key Lab of Multi-Modal Data Fusion and Intelligent Healthcare Suzhou City University Suzhou China

ISBN: (数字)9798331541699

ISBN: (纸本)9798331541705

To effectively address the issue of inadequate accuracy and timeliness in industrial data classification, this paper proposes a fusion classification model based on time series (DT-RF-MLP) for loss prediction of electrical work equipment. Firstly, data information is extracted from the dataset and features are constructed based on the data information to enhance the diversity of data features. Secondly, redundant and highly correlated features are removed by quantifying the correlation degree between the features to simplify the model inputs. On this basis, a fusion classification model is constructed and comparative experiments are conducted with a single model to validate the advantages of the fusion model in terms of prediction performance. The experimental results demonstrate that the model markedly enhances prediction accuracy while concurrently reducing the duration of the model run.

关键词： Accuracy Correlation Service robots Time series analysis Predictive models Feature extraction Data models Power systems Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

From Rule-Based Models to Deep Learning Transformers Architectures for Natural Language Processing and Sign Language Translation Systems: Survey, Taxonomy and Performance Evaluation

arXiv

引用

arXiv 2024年

作者： Shahin, Nada Ismail, Leila Intelligent Distributed Computing and Systems Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates Emirates Center for Mobility Research United Arab Emirates University Abu Dhabi United Arab Emirates

With the growing Deaf and Hard of Hearing population worldwide and the persistent shortage of certified sign language interpreters, there is a pressing need for an efficient, signs-driven, integrated end-to-end translation system, from sign to gloss to text and vice-versa. There has been a wealth of research on machine translations and related reviews. However, there are few works on sign language machine translation considering the particularity of the language being continuous and dynamic. This paper aims to address this void, providing a retrospective analysis of the temporal evolution of sign language machine translation algorithms and a taxonomy of the Transformers architectures, the most used approach in language translation. We also present the requirements of a real-time Quality-of-Service sign language machine translation system underpinned by accurate deep learning algorithms. We propose future research directions for sign language translation *** Codes I.2, I.2.7, I.4, I.4.9 © 2024, CC BY.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

HealthEdge: A Machine Learning-Based Smart Healthcare Framework for Prediction of Type 2 Diabetes in an Integrated IoT, Edge, and Cloud computing System

引用

Procedia Computer Science 2023年 220卷 331-338页

作者： Alain Hennebelle Huned Materwala Leila Ismail Independent Researcher Melbourne Australia Intelligent Distributed Computing and Systems (INDUCE) Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates Cloud Computing and Distributed Systems (CLOUDS) Lab School of Computing and Information Systems The University of Melbourne Australia

Diabetes Mellitus has no permanent cure to date and is one of the leading causes of death globally. The alarming increase in diabetes calls for the need to take precautionary measures to avoid/predict the occurrence of diabetes. This paper proposes HealthEdge, a machine learning-based smart healthcare framework for type 2 diabetes prediction in an integrated IoT-edge-cloud computing system. Numerical experiments and comparative analysis were carried out between the two most used machine learning algorithms in the literature, Random Forest (RF) and Logistic Regression (LR), using two real-life diabetes datasets. The results show that RF predicts diabetes with 6% more accuracy on average compared to LR.

关键词： Artificial Intelligence (AI) Cloud computing Diagnosis Digital Health Edge computing eHealth Internet of Things (IoT) Logisitic Regression Machine Learning Prognosis Random Forest Risk Factors Smart Connected Healthcare Type 2 Diabetes Mellitus

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Knowledge-aware Multi-Interest intelligent Model for Sequential Recommendation 19

Attention-Based Knowledge-aware Multi-Interest Intelligent M...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalab.e computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Li, Yang Li, Qianmu Meng, Shunmei Hou, Jun Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China Wuyi University Intelligent Manufacturing Department Jiangmen China Nanjing University State Key Lab. for Novel Software Technology Nanjing China Nanjing Vocational University of Industry Technology School of Social Science Nanjing China

ISBN: (纸本)9798350346558

As a fundamental means of intelligent service, recommender systems have shown a trend of diversification. Sequential recommendation, a class of time-aware methods, aims to predict the user's next click. Multi-interest representation is a hot topic in recommender systems, but the research on how to apply multi-interest into sequences is still in the minority. And many methods will introduce knowledge graph to improve the representation of items, but how to consider both knowledge graph and user's multi-interest in sequential recommendation has become a temporary blank. In this paper, we propose an attentive sequential recommendation with knowledge-aware multi-interest module (AKAMI). Items are embedded from the sequence's structure and user's interests. Specifically, we represent items by stacking self-attention layers to mine the internal correlation of the sequence. Meanwhile, we segment the sequence via the common neighbors in the knowledge graph and cast the user's multi-interest based on the aggregation of subsequences. Multi-interests are integrated into item representation by the gating network adaptively. Comprehensive experiments on two real-world datasets show that the proposed model performs better than various representative methods under different evaluation metrics. Additionally, we also visually explain the model through a case study. © 2022 IEEE.

关键词： Recommender 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：