检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pan, Quyang Sun, Sheng Wu, Zhiyuan Wang, Yuwei Liu, Min Gao, Bo Wang, Jingyuan The State Key Laboratory of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China The University of Chinese Academy of Sciences Beijing China The Zhongguancun Laboratory Beijing China The School of Computer and Information Technology The Engineering Research Center of Network Management Technology for High-Speed Railway Ministry of Education Beijing Jiaotong University Beijing China The School of Computer Science and Engineering Beihang Unversity Beijing China

Federated Edge Learning (FEL) has emerged as a promising approach for enabling edge devices to collaboratively train machine learning models while preserving data privacy. Despite its advantages, practical FEL deployment faces significant challenges stemming from device constraints and device-server interactions, necessitating heterogeneous, user-adaptive model training with limited and uncertain communication conditions. Knowledge Cache-driven Federated Learning (FedCache) is a promising architecture that enables communication-efficient and heterogeneous-aware collaborative training in edge computing scenarios. However, previous work is limited by the intrinsic nature of logits-based interactions, leading to performance bottlenecks due to the poor richness of exchanged information for on-device model optimization. To tackle this issue, we introduce FedCache 2.0, a novel personalized FEL architecture that enhances the exchange of optimization insights while delivering state-of-the-art performance with efficient communication. FedCache 2.0 incorporates the benefits of both dataset distillation and knowledge cache-driven federated learning by storing and organizing distilled data as knowledge in the server-side knowledge cache, allowing devices to periodically download and utilize personalized knowledge for local model optimization. Moreover, a device-centric cache sampling strategy is introduced to tailor transferred knowledge for individual devices within controlled communication bandwidth. Extensive experiments on five datasets covering image recognition, audio understanding, and mobile sensor data mining tasks demonstrate that (1) FedCache 2.0 significantly outperforms state-of-the-art methods regardless of model structures, data distributions, and modalities. (2) FedCache 2.0 can train splendid personalized on-device models with at least ×28.6 improvement in communication efficiency. Our code is available at https://***/poppanda/FedCache2. 0. Copyright © 2

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Agent for Failure-aware Job scheduling in High-Performance computing

Deep Reinforcement Agent for Failure-aware Job scheduling in...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Kang Yang Rongyu Cao Yueyuan Zhou Jiawei Zhang En Shao Guangming Tan State Key Laboratory of Computer Architecture Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665408790

Job scheduling is crucial in high-performance computing (HPC), which is dedicated to deciding when and which jobs are allocated to the system and placing the jobs on which resources, by considering multiple scheduling goals. Along with the incremental of various resources and dazzling deep learning training (DLT) workloads, job failure becomes a quite common issue in HPC, which will affect user satisfaction and cluster utilization. To alleviate the influence of hardware and software errors as much as possible, in this paper, we aim to tackle the problem of failure-aware job scheduling in HPC clusters. Inspired by the success of previous studies of deep reinforcement learning-driven job scheduling, we propose a novel HPC scheduling agent named FARS (Failure-aware RL-based scheduler) by considering the effects of job failures. On the one hand, a neural network is applied to map the information of raw cluster and job states to job placement decisions. On the other hand, to consider the influence of job failure for user satisfaction and cluster utilization, FARS leverages make-span of the entire workload as the training objective. Additionally, effective exploration and experience replay techniques are applied to obtain effectively converged agent. To evaluate the capability of FARS, we design extensive trace-based simulation experiments with the popular DLT workloads. The experimental results show that, compared with the best baseline model, FARS obtains 5.69% improvement of average make-span under different device error rates. Together, our FARS is an ideal candidate for failure-aware job scheduler in HPC clusters.

关键词： Training Deep learning Processor scheduling Error analysis Computational modeling Conferences Neural networks

来源：评论

学校读者我要写书评

暂无评论

Cold-Start Link Prediction via Weighted Symmetric Nonnegative Matrix Factorization with Graph Regularization

引用

computer Systems Science & Engineering 2022年第12期43卷 1069-1084页

作者： Minghu Tang Wei Yu Xiaoming Li Xue Chen Wenjun Wang Zhen Liu key Laboratory of Artificial Intelligence Application Technology State Ethnic Affairs Commission Qinghai Minzu UniversityXining810007China School of Computer Science Qinghai Minzu UniversityXining810007China College of Intelligence and Computing Tianjin UniversityTianjin300350China School of International Business Zhejiang Yuexiu UniversityShaoxing312069China Law School Tianjin UniversityTianjin300072China Graduate School of Engineering Nagasaki Institute of Applied ScienceNagasaki851-0193Japan

Link prediction has attracted wide attention among interdisciplinaryresearchers as an important issue in complex network. It aims to predict the missing links in current networks and new links that will appear in future *** the presence of missing links in the target network of link prediction studies, the network it processes remains macroscopically as a large connectedgraph. However, the complexity of the real world makes the complex networksabstracted from real systems often contain many isolated nodes. This phenomenon leads to existing link prediction methods not to efficiently implement the prediction of missing edges on isolated nodes. Therefore, the cold-start linkprediction is favored as one of the most valuable subproblems of traditional linkprediction. However, due to the loss of many links in the observation network, thetopological information available for completing the link prediction task is extremely scarce. This presents a severe challenge for the study of cold-start link prediction. Therefore, how to mine and fuse more available non-topologicalinformation from observed network becomes the key point to solve the problemof cold-start link prediction. In this paper, we propose a framework for solving thecold-start link prediction problem, a joint-weighted symmetric nonnegative matrixfactorization model fusing graph regularization information, based on low-rankapproximation algorithms in the field of machine learning. First, the nonlinear features in high-dimensional space of node attributes are captured by the designedgraph regularization term. Second, using a weighted matrix, we associate the attribute similarity and first order structure information of nodes and constrain eachother. Finally, a unified framework for implementing cold-start link prediction isconstructed by using a symmetric nonnegative matrix factorization model to integrate the multiple information extracted together. Extensive experimental validationon five rea

关键词： Link prediction cold-start nonnegative matrix factorization graph regularization

来源：评论

学校读者我要写书评

暂无评论

TNASP: a transformer-based NAS predictor with a self-evolution framework 21

TNASP: a transformer-based NAS predictor with a self-evoluti...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Shun Lu Jixiang Li Jianchao Tan Sen Yang Ji Liu Research Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Kuaishou Technology

ISBN: (纸本)9781713845393

Predictor-based Neural architecture Search (NAS) continues to be an important topic because it aims to mitigate the time-consuming search procedure of traditional NAS methods. A promising performance predictor determines the quality of final searched models in predictor-based NAS methods. Most existing predictor-based methodologies train model-based predictors under a proxy dataset setting, which may suffer from the accuracy decline and the generalization problem, mainly due to their poor abilities to represent spatial topology information of the graph structure data. Besides the poor encoding for spatial topology information, these works did not take advantage of the temporal information such as historical evaluations during training. Thus, we propose a Transformer-based NAS performance predictor, associated with a Laplacian matrix based positional encoding strategy, which better represents topology information and achieves better performance than previous state-of-the-art methods on NAS-Bench-101, NAS-Bench-201, and DARTS search space. Furthermore, we also propose a self-evolution framework that can fully utilize temporal information as guidance. This framework iteratively involves previous evaluation information as constraints into current optimization iteration, thus further improving the performance of our predictor. Such framework is model-agnostic, thus can enhance performance on various backbone structures for the prediction task. Our proposed method helped us rank 2nd among all teams in CVPR 2021 NAS Competition Track 2: Performance Prediction Track.

关键词：

来源：评论

学校读者我要写书评

暂无评论

KFS-LIO: key-Feature Selection for Lightweight Lidar Inertial Odometry

KFS-LIO: Key-Feature Selection for Lightweight Lidar Inertia...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Wei Li Yu Hu Yinhe Han Xiaowei Li Research Center for Intelligent Computing Systems Institute of Computing Technology the Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Architecture Institute of Computing Technology the Chinese Academy of Sciences Beijing China

Feature-based lidar odometry methods have attracted increasing attention due to their low computational cost. However, theoretically analysis of the effect of extracted features on pose estimation is still lacked. In this paper, we propose a method of key-feature selection for lightweight lidar inertial odometry, KFS-LIO, to further enhance the real-time performance by selecting the most effective subset of lidar feature constraints. Aiming at explaining the correlation between the feature distribution and state errors, a quantitative evaluation method of lidar constraints is introduced. In addition, to avoid recalculating the reprojection matrices in de-skewing step, we use the intermediate variables in IMU preintegration to compensate for lidar motion distortion. The experimental results demonstrate that KFS-LIO can reduce half of the LOAM features and provide comparable accuracy with the state-of-the-art odometry.

关键词： Laser radar Correlation Automation Conferences Pose estimation Feature extraction Distortion

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Framework for TCP to Achieve Flexible QoS Control in Mobile Data Networks

A Data-Driven Framework for TCP to Achieve Flexible QoS Cont...

引用

International Workshop on Quality of Service

作者： Jiaqi Yao Ke Liu Ting Liang Theophilus A. Benson Jack Y. B. Lee Vaneet Aggarwal Yungang Bao Mingyu Chen Henan Institute of Advanced Technology Zhengzhou University State Key Lab of Processors and Research Center for Advanced Computer Systems Institute of Computing Technology CAS University of Chinese Academy of Sciences Carnegie Mellon University The Chinese University of Hong Kong Purdue University Zhongguancun Laboratory

Learning-based approaches have shown their great potential to adapt themselves to various environments (e.g., PCC and Sprout). Unfortunately, they do not consistently achieve superior QoS across different network conditions and configurations in mobile networks. Furthermore, although they can offer multiple application objectives by adjusting a preference weight vector, it is challenging for users to accurately express an application objective with a weight vector. In this work, we argue that, if configured correctly, the delay-based TCP scheme can outperform learned ones, and allow users to directly specify their objectives. To this end, we propose Post-QoS Analysis (PQSA), a data-driven framework that trains the key QoS-impacting parameters of the scheme to capture the statistical correlations between QoS objectives, network conditions, and configurations, thereby determining the optimal parameter-set that meets the user-defined QoS objective under different network conditions and configurations. To support this, we enhance conventional delay-based TCP design to develop a Generalized TCP-like Rate controller (GR) by exporting three key parameters. Extensive evaluations show that PQSA-optimized GR outperforms existing schemes in different scenarios consistently, and enables service providers to control the QoS flexibly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Classification of Plasmodium for Malaria Diagnosis based on Ensemble Neural Network 2020

Automatic Classification of Plasmodium for Malaria Diagnosis...

引用

2nd International Conference on Intelligent Medicine and Image Processing, IMIP 2020

作者： Shi, Lulin Guan, Zhen Liang, Chunzi You, Haihang State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China Central South Hospital of Wuhan University Wuhan China

ISBN: (纸本)9781450377799

Malaria is one of the important public health issues of global concern. It is a kind of infectious disease caused by Plasmodium which can endanger human life and health. The examination of Plasmodium blood smear is the main method to diagnose malaria. Applying machine learning method to automatically analyze malaria smear images is very important for rapid diagnosis and surveillance of malaria. However, the existing machine learning methods need further improvement in feature extraction and generalization ability. For this reason, this paper introduces an ensemble neural network to automatically learn more accurate image features and achieve automatic classification of malaria images. In addition, we propose an adaptive threshold control method for cell segmentation, and then put the cell as center to extract images to obtain the training dataset, which solves the noise problem caused by sliding window cutting. And the idea of transfer learning is applied to solve the problem of shortage of training data. We additionally apply the proposed method to malaria image recognition and achieve 94.58% accuracy. The experimental results show that the model has good robustness and generalization ability and provides a valid data processing method for clinical malaria rapid diagnosis application. © 2020 ACM.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

In-situ NAS: A Plug-and-Search Neural architecture Search framework across hardware platforms

引用

IEEE Transactions on computers 2025年

作者： Lv, Hao Zhang, Lei Wang, Ying Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China State Key Laboratory of Computer Architecture China

Hardware-aware Neural architecture Search (HW-NAS) has garnered significant research interest due to its ability to automate the design of neural networks for various hardware platforms. Prevalent HW-NAS frameworks often use fast predictors to estimate network performance, bypassing the time-consuming actual profiling step. However, the resource-intensive nature of building these predictors and their accuracy limitations hinder their practical use in diverse deployment scenarios. In response, we emphasize the indispensable role of actual profiling in HW-NAS and explore efficiency optimization possibilities within the HW-NAS framework. We provide a systematic analysis of profiling overhead in HW-NAS and identify many redundant and unnecessary operations during the search phase. We then optimize the workflow and present Insitu NAS, which leverages similarity features and exploration history to eliminate redundancy and improve runtime efficiency. In-situ NAS also offers simplified interfaces to ease the user’s effort in managing the complex device-dependent profiling flow, enabling plug-and-search functionality across diverse hardware platforms. Experimental results show that In-situ NAS achieves an average 10x speedup across different hardware platforms while reducing the search overhead by 8x compared to predictor-based approaches in various deployment scenarios. Additionally, In-situ NAS consistently discovers networks with better accuracy (about 1.5%) across diverse hardware platforms compared to predictor-based NAS. © 1968-2012 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

MHCD: Multi-Hierarchy Interactive Constraint-Aware Cognitive Diagnosis Framework

引用

Expert Systems with Applications 2025年 283卷

作者： Sun, Xinjie Zhang, Kai Shen, Shuanghong Wang, Fei Gong, Weiyin Yang, Lina Ma, Yuling Huo, Xingying Liu, Qi School of Computer Science Liupanshui Normal University Liupanshui China School of Computer Science and Technology University of Science and Technology of China Hefei China School of Artificial Intelligence and Data Science University of Science and Technology of China Hefei China State Key Laboratory of Cognitive Intelligence Hefei China School of Computing National University of Singapore Singapore Singapore Shandong Jianzhu University Jinan China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

Cognitive Diagnosis (CD) is a fundamental aspect of educational data mining that focuses on assessing students’ mastery of specific knowledge domains by analyzing their response patterns. However, traditional CD frameworks often fail to reasonably model students’ true knowledge state due to insufficient constraints for automatic inference, particularly overlooking the hierarchical relationships among explicit behavioral records. This limitation undermines both the rationality and interpretability of diagnostic outcomes. To address these challenges, we propose an innovative Multi-Hierarchy Interactive Constraint-aware Cognitive Diagnosis (MHCD) framework. This framework first identifies and constructs the hierarchical relationships of explicit records in real-world educational contexts. It then delves into feature interactions across multiple hierarchies and achieves more accurate and reasonable knowledge state modeling through an iterative constraint-aware strategy. Finally, it integrates multi-hierarchy interaction-aware features with personalized features, significantly enhancing the expressive power of both individual and hierarchical attributes. Experimental results demonstrate that MHCD achieves notable improvements in diagnostic accuracy, rationality, and interpretability, while seamlessly integrating into existing cognitive diagnosis frameworks to further enhance their overall performance. © 2025

关键词： Text mining

来源：评论

学校读者我要写书评

暂无评论

Near 100%spectral-purity photons from reconfigurable micro-rings

引用

Chinese Physics B 2020年第11期29卷 135-139页

作者： Pingyu Zhu Yingwen Liu Chao Wu Shichuan Xue Xinyao Yu Qilin Zheng Yang Wang Xiaogang Qiang Junjie Wu Ping Xu Institute for Quantum Information&State Key Laboratory of High Performance Computing College of ComputerNational University of Defense TechnologyChangsha 410073China National Innovation Institute of Defense Technology AMSBeijing 100071China National Laboratory of Solid State Microstructures and School of Physics Nanjing UniversityNanjing 210093China

We propose an on-chip reconfigurable micro-ring to engineer the spectral-purity of *** micro-ring resonator is designed to be coupled by one or two asymmetric Mach-Zehnder interferometers and the coupling coefficients hence the quality-factors of the pump and the converted photons can be dynamically changed by the interferometer’s internal *** calculate the joint-spectrum function and obtain the spectral-purity of photons and Schmidt number under different *** show that it is a dynamical method to adjust the spectral-purity and can optimize the spectralpurity of photons up to near 100%.The condition for high-spectral-purity photons is ensured by the micro-ring itself,so it overcomes the trade-off between spectral purity and brightness in the traditional post-filtering *** scheme is robust to fabrication variations and can be successfully applied in different fabrication labs and different *** high-spectral-purity photons will be beneficial for quantum information processing like Boson sampling and other quantum algorithms.

关键词： spectral-purity micro-ring Mach–Zehnder interferometer

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：