检索结果-内蒙古大学图书馆

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Wang, Jihe Wu, Ying Wang, Danghui School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798400706011

Training big graph neural networks (GNNs) in distributed systems is quite time-consuming mainly because of the ubiquitous aggregate operations that involve a large amount of cross-partition communication for collecting embeddings/gradients during the forward and backward propagation. To reduce the volume of the communication, some recent approaches focused on decaying each of connections via sampling, quantifying, or delaying until satisfactory trade-off are obtained between volume and accuracy. However, when applied to popular GNNs, those approaches are found to be bounded by a common volume/accuracy Pareto frontier which shows that the decaying for individual connection cannot further accelerate the aggregate of training. In this work, SC-GNN, a semantic compression of the cross-partition communication, is proposed to concentrate a group of connections as a high-level semantics and transmit to a target partition. Since carrying the overall intent of a group, the semantics can keep transferring the interactions, i.e., embeddings/gradients, between a pair of remote partitions until GNN models converge. In addition, a connection-pattern based differential optimization is proposed to further prune those weak connections, while guaranteeing the training accuracy. The results show that, for multi-field datasets, the compression rate of SC-GNN is 40.8 × higher than SOTA methods and the epoch time is reduced to 31.8% on average. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Simulation Illuminates Scientific Problems of Organised Complexity

arXiv

引用

arXiv 2024年

作者： Wang, Cheng Wang, Chuwen Zhang, Wang Zhao, Yu Zeng, Shirong Ning, Ronghui Jiang, Changjun Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China Shanghai Artificial Intelligence Laboratory Shanghai China

As artificial intelligence becomes increasingly prevalent in scientific research, data-driven methodologies appear to overshadow traditional approaches in resolving scientific problems. In this Perspective, we revisit a classic classification of scientific problems and acknowledge that a series of unresolved problems remain. Throughout the history of researching scientific problems, scientists have continuously formed new paradigms facilitated by advances in data, algorithms, and computational power. To better tackle unresolved problems, especially those of organised complexity, a novel paradigm is necessitated. While recognising that the strengths of new paradigms have expanded the scope of resolvable scientific problems, we aware that the continued advancement of data, algorithms, and computational power alone is hardly to bring a new paradigm. We posit that the integration of paradigms, which capitalises on the strengths of each, represents a promising approach. Specifically, we focus on next-generation simulation (NGS), which can serve as a platform to integrate methods from different paradigms. We propose a methodology, sophisticated behavioural simulation (SBS), to realise it. SBS represents a higher level of paradigms integration based on foundational models to simulate complex systems, such as social systems involving sophisticated human strategies and behaviours. NGS extends beyond the capabilities of traditional mathematical modelling simulations and agent-based modelling simulations, and therefore, positions itself as a potential solution to problems of organised complexity in complex systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

A credible individual behavior profiling method for online payment fraud detection 21

A credible individual behavior profiling method for online p...

引用

4th International Conference on Data Storage and Data Engineering, DSDE 2021

作者： Cui, Jipeng Yan, Chungang Wang, Cheng Key Laboratory of the Ministry of Education for Embedded System and Service Computing Department of Computer Science and Engineering Tongji University China

ISBN: (纸本)9781450389303

Online payment fraud detection relies on a credible characterization of individual behaviors. Existing individual behavior profiling methods have three problems in credibility. Firstly, they solely regard users as individuals to model and fail to credibly characterize the whole behavior patterns of transactions. Secondly, they cannot make full use of the general information among similar individuals due to the heterogeneity of transaction attributes. Thirdly, they are not capable of utilizing the label information of transactions credibly. Faced with these challenges, we propose a credible method for individual behavior profiling that consists of two steps. The first step is the construction of the credible individual behavior profiling framework. To begin with, the concept of individuals is generalized and the credible transaction description is given. Afterwards, based on the co-occurrence information of transaction attributes, the credible behavior condition is defined to set a limit to individual behavior patterns. The second step is the implementation of the framework. For this purpose, the original fraud detection problem is transformed into a pseudo-recommender system problem with a co-occurrence mapping process. In order to guarantee the credible behavior constraint, a credible recommendation algorithm is designed to collaboratively restore both the ranking and rating information of the pseudo-rating matrices. Besides, an embedding based approach is adopted to parameterize the proposed model. Experiments on an online payment transaction dataset demonstrate the effectiveness of our proposed method. © 2021 ACM.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Implementation Analysis of Reachability Graph and Its Application in Net Learning

Implementation Analysis of Reachability Graph and Its Applic...

引用

computer, Control and Robotics (ICCCR), International Conference on

作者： Mingjian Guang Chungang Yan Zihao Lu Rui Duan Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China

ISBN: (数字)9798350373141

ISBN: (纸本)9798350373158

Reachability represents the most fundamental dynamic property of Petri nets. The reachability graph serves as a crucial tool for analyzing reachability, and its generation algorithm has garnered widespread attention. However, most of the existing work has focused primarily on the accuracy of the generation algorithm, often overlooking computational and time costs. Therefore, this paper concentrates on the implementation of reachability graphs and proposes three implementation methods: definition-based (DB), matrix-based (MB), and a fast generation method without self-loops (FG). Through comprehensive experiments, we evaluate and analyze the running speed and applicable scenarios of these three methods. Furthermore, we have successfully applied the proposed methods in net learning.

关键词： Digital control Costs Accuracy Heuristic algorithms Petri nets Benchmark testing Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Numerical Analysis of Bi-fluid PV/T Hybrid Collector Using the Finite Difference Method 6th

Numerical Analysis of Bi-fluid PV/T Hybrid Collector Using t...

引用

6th International Conference on Wireless Technologies, embedded and Intelligent systems, WITS 2020

作者： El Manssouri, Oussama Hajji, Bekkay Gagliano, Antonio Tina, Giuseppe Marco Renewable Energy Embedded System and Data Processing Laboratory National School of Applied Sciences Mohamed First University Oujda Morocco DIEEI: Department of Electric Electronic and Computer Engineering University of Catania Catania Italy

ISBN: (纸本)9789813368927

The PV/T is called as a hybrid bi-fluid type solar collector when both fluids (water and air) are used as working fluids. This type of collector provide a wide range of thermal applications and several modes can be executed depending on energy needs and applications: air mode, water mode and simultaneous mode (air and water). This paper presents a numerical analysis of PV/T bi-fluid collector using the finite difference method. Energy balance equations were established for each layer and solved using the Gauss–Seidel iteration method. The performance of the PV/T hybrid is evaluated according to the operating mode of the fluid (independently and simultaneously). The simulation results are compared with literature (Modeling and performances assessments of PV/T bifluid hybrid collector: Three cooling modes operation case. https://***/10.1109/iceit48248.2020.9113233, [10]), and indicate that when both fluids are used simultaneously, the overall electrical and thermal performance of the hybrid collector is considered satisfactory compared to the situation where two fluids operate independently. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Finite difference method

来源：评论

学校读者我要写书评

暂无评论

Heuristic Elastic Scaling for Kubernetes Heterogeneous Microservices 21

Heuristic Elastic Scaling for Kubernetes Heterogeneous Micro...

引用

21st International Conference on Networking, Sensing and Control, ICNSC 2024

作者： Wang, Song He, Sheng Ning, Yishuang Gao, Xiang Ding, Zhijun The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai201804 China The Department of Computer Science and Technology Tongji University Shanghai201804 China Kingdee Research Kingdee International Software Group Co. Ltd Shenzhen518057 China Intelligent Computing Facility Innovation Center ZhejiangLab Hangzhou30012 China

ISBN: (纸本)9798350365221

Kubernetes has become the basic platform for building cloud native applications. However, existing horizontal scaling methods based on Kubernetes have problems with resource redundancy. Furthermore, the combined horizontal and vertical scaling based on Kubernetes takes a long time. Regarding the issue above, first, we describe the execution processes of three scaling techniques and compare them in different dimensions;second, we construct a formal elastic scaling model for expansion scenarios, with the goal of minimizing the total cost;and third, we introduce a heuristic expansion algorithm after balancing resource redundancy and execution time as the heuristic information. The experiment results show that the elastic scaling algorithm proposed in this paper achieves better performance than other algorithms. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Learning Topic Emotion and Logical Semantic for Video Paragraph Captioning

SSRN

引用

SSRN 2024年

作者： Li, Qinyu Wang, Hanli Yi, Xiaokai Department of Computer Science & Technology Tongji University Shanghai201804 China Key Laboratory of Embedded System & Service Computing Ministry of Education Tongji University Shanghai200092 China

Video paragraph captioning aims to generate multiple descriptive sentences for videos, which strive to replicate human writing in accuracy, logicality, and richness. However, current research focuses on the accuracy and temporal order of events, ignoring emotion and other critical logical relations embedded in human language, such as causal and adversative relations. The ignorance impairs the reasonable transition across generated event descriptions and restricts the vividness of expression, resulting in a gap from the standard of human language. To resolve the problem, a framework that integrates logic and emotion representation learning is proposed to narrow the gap. Concretely, a large-scale inter-event relation corpus is constructed based on the EMVPC dataset. This corpus is named EMVPC-EvtRel (standing for "EMVPC-Event Relations") and contains six widely-used logical relations in human writing, 127 explicit inter-sentence connectives, and over 20,000 pairs of event segments with newly annotated logical relations. A logical semantic representation learning method is developed for recognizing the dependencies between visual events, thereby enhancing the characteristics of video contents and boosting the logicality of generated paragraphs. Moreover, a fine-grained emotion recognition module is designed to uncover emotion features embedded in videos. Finally, experimental results on the EMVPC dataset demonstrate the superiority of the proposed method compared to existing state-of-the-art approaches. © 2024, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Personalized Medical Federated Learning Based on Mutual Knowledge Distillation in Object Heterogeneous Environment 1st

Personalized Medical Federated Learning Based on Mutual Kno...

引用

1st Conference on Blockchain and Web3.0 Technology Innovation and Application, BWTAC 2024

作者： Ni, Lina Song, Chenglin Zhao, Hanmo Tang, Yuncan Ma, Yunshen Zhang, Jinquan College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Key Laboratory of the Ministry of Education for Embedded System and Service Computing Tongji University Shanghai201804 China

ISBN: (纸本)9789819794119

Federated Learning (FL), hailed as a potent approach in merging medical expertise, promises to elevate collaborative efforts among healthcare institutions while safeguarding the privacy and security of sensitive medical data, thereby energizing the trajectory of intelligent healthcare advancements. However, the diversity in training objectives across medical institutions can diminish their active participation in a unified federated training process. To address this issue of waning enthusiasm due to diverse training goals, in this paper, we propose Personalized Medical Federated Learning method based on Mutual Distillation Knowledge (pFedMKD). Specifically, we propose a similarity-based mutual distillation model selection algorithm that reduces interference among medical institutions with notably diverse data distributions. Moreover, we develop a server-side local model update method leveraging mutual knowledge distillation, enabling each local model to gain beneficial insights for personalization from analogous models. Additionally, we formulate a personalized model update method utilizing knowledge distillation from specifically labeled samples, thereby improving the performance of personalized models. Experimental results demonstrate that compared to the baseline algorithm, pFedMKD can more effectively address the target heterogeneity problem among different medical institutions, enabling each institution to achieve higher personalized performance in federated learning tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Federated Learning Based on Device Performance in a Heterogeneous Environment of Medical Computing Devices 1st

Adaptive Federated Learning Based on Device Performance in...

引用

1st Conference on Blockchain and Web3.0 Technology Innovation and Application, BWTAC 2024

作者： Zhang, Jinquan Wang, Chongbo Yang, Rendong Tang, Yuncan Ma, Yunshen Ni, Lina College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Key Laboratory of the Ministry of Education for Embedded System and Service Computing Tongji University Shanghai201804 China

ISBN: (纸本)9789819794119

Federated Learning (FL), as one of the effective methods to solve the problem of medical data silos, can promote mutual cooperation among medical institutions under the premise of safeguarding the privacy and security of medical data, and effectively promote the development of intelligent medical treatment. However, the characteristics of medical data with multiple sources and heterogeneity bring certain challenges to the application of federated learning in the medical field. Due to the wide range of medical data sources, some medical institutions are unable to complete the federated learning training task on time due to the limitation of device performance, which leads to the failure of federated learning training. To address the problem of heterogeneity of computing devices among medical institutions that may cause some clients to fall behind, we propose an Adaptive Federated Learning based on Device Performance (AFedDP) method. Specifically, we design an adaptive local model training method to reduce the computational burden of medical institutions with poor equipment performance in the local model training process by adaptively constructing a local training model. Additionally, we propose a hierarchical model aggregation algorithm based on dynamic weight. This allows the heterogeneous adaptive local model to actively participate in the global model aggregation, making full use of the local data of each medical institution and improving the performance of the global model. Finally, we design an aggregation weight update algorithm based on momentum optimization to enhance the stability of global model aggregation. This algorithm updates contribution and aggregation weight with the idea of momentum optimization. Simulation experiments demonstrate that AFedDP achieves higher accuracy compared to the baseline algorithm. AFedDP can better address the issue of some devices being unable to participate in federated training properly. © The Author(s), under exclusive lic

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Depression Scale Dictionary Decomposition Framework for Multimodal Automatic Depression Level Prediction

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年第6期35卷 6195-6210页

作者： Niu, Mingyue Wang, Xu Gong, Jibing Liu, Bin Tao, Jianhua Schuller, Bjorn W. Yanshan University School of Information Science and Engineering Hebei province Qinhuangdao066004 China Hebei Key Laboratory of Computer Virtual Technology and System Integration China Technology Co. Ltd Bejing100022 China Bejing100190 China Tsinghua University Department of Automation Bejing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China University of Augsburg ZD.B. Chair of Embedded Intelligence for Health Care and Wellbeing Augsburg Germany Glam - Group on Language Audio and Music United Kingdom

Currently, many researchers aim to achieve automatic depression level prediction via speech and video behavior analysis. However, previous works have struggled to decompose audio and video sequences into the information related to and unrelated to depression scores, hindering the model's perception of depression cues. Besides, previous works implement multimodal fusion using attention mechanisms or linear layers, but failed to simultaneously consider the Euclidean relationship among tokens and the non-Euclidean relationship among channels, which bring limitations in capturing depression cues. In response to the above issues, we propose a depression scale dictionary decomposition framework, which mainly includes a Bidirectional Dictionary Decomposition (BDD) module and a Bidirectional Multimodal Fusion (BMF) module. The BDD module can use the dictionaries generated based on the depression scale to semantically decompose audio and video sequences into the information related to and unrelated to depression scores along token and channel dimensions for promoting depression cue perception. Moreover, considering the respective characteristics of tokens and channels, the BMF module uses linear layers and graph convolution to achieve cross-modal mixing, which is used to aggregate audio and video sequences for predicting depression levels. The validation on AVEC 2013, AVEC 2014 and DAIC-WOZ datasets demonstrates our method's superiority. © 1991-2012 IEEE.

关键词： Boolean functions

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：