检索结果-内蒙古大学图书馆

Dynamic QoS-Driven Framework for Co-Scheduling of Distributed Long-Running Applications on Shared Clusters

学校读者我要写书评

暂无评论

IEEE Transactions on Cloud computing 2025年

作者： Zhu, Jianyong Wang, Hongtao Su, Pan Wang, Yang Pan, Weihua North China Electric Power University Department of Computer China Hebei Key Laboratory of Knowledge Computing for Energy & Power China Ministry of Education Engineering Research Center of Intelligent Computing for Complex Energy Systems China

Cloud service providers typically co-locate various workloads within the same production cluster to improve resource utilization and reduce operational costs. These workloads primarily consist of batch analysis jobs composed of multiple parallel short-running tasks and long-running applications (LRAs) that continuously reside in the system. The adoption of microservice architecture has led to the emergence of distributed long-running applications (DLRAs), which enhance deployment flexibility but pose challenges in detecting and investigating QoS violations due to workload variability and performance propagation across microservices. State-of-the-art resource managers are only responsible for resource allocation among applications/jobs and do not prioritize runtime QoS aspects, such as applicationlevel latency. To address this, we introduce Prank, a QoSdriven resource management framework for co-located workloads. Prank incorporates a non-intrusive performance anomaly detection mechanism for DLRAs and proposes a root cause localization algorithm based on PageRank-weighted analysis of performance anomalies. Moreover, it dynamically balances resource allocation between DLRAs and co-located batch jobs on nodes hosting critical microservices, optimizing for both DLRA performance and overall cluster efficiency. Experimental results demonstrate that Prank outperforms state-of-the-art baselines, reducing DLRA tail latency by over 38% while increasing batch job completion time by no more than 21% on average © 2013 IEEE.

关键词： Resource allocation

TYPE-SUPERVISED SEQUENCE LABELING BASED ON THE HETEROGENEOUS STAR GRAPH FOR NAMED ENTITY RECOGNITION

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wen, Xueru Zhou, Changjiang Tang, Haotian Liang, Luguang Jiang, Yu Qi, Hong College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China

Named entity recognition is a fundamental task in natural language processing, identifying the span and category of entities in unstructured texts. The traditional sequence labeling methodology ignores the nested entities, i.e. entities included in other entity mentions. Many approaches attempt to address this scenario, most of which rely on complex structures or have high computation complexity. The representation learning of the heterogeneous star graph containing text nodes and type nodes is investigated in this paper. In addition, we revise the graph attention mechanism into a hybrid form to address its unreasonableness in specific topologies. The model performs the type-supervised sequence labeling after updating nodes in the graph. The annotation scheme is an extension of the single-layer sequence labeling and is able to cope with the vast majority of nested entities. Extensive experiments on public NER datasets reveal the effectiveness of our model in extracting both flat and nested entities. The method achieved state-of-the-art performance on both flat and nested datasets. The significant improvement in accuracy reflects the superiority of the multi-layer labeling strategy. Copyright © 2022, The Authors. All rights reserved.

关键词： Natural language processing systems

END-TO-END ENTITY DETECTION WITH PROPOSER AND REGRESSOR

学校读者我要写书评

暂无评论

arXiv 2022年

Named entity recognition is a traditional task in natural language processing. In particular, nested entity recognition receives extensive attention for the widespread existence of the nesting scenario. The latest research migrates the well-established paradigm of set prediction in object detection to cope with entity nesting. However, the manual creation of query vectors, which fail to adapt to the rich semantic information in the context, limits these approaches. An end-to-end entity detection approach with proposer and regressor is presented in this paper to tackle the issues. First, the proposer utilizes the feature pyramid network to generate high-quality entity proposals. Then, the regressor refines the proposals for generating the final prediction. The model adopts encoder-only architecture and thus obtains the advantages of the richness of query semantics, high precision of entity localization, and easiness of model training. Moreover, we introduce the novel spatially modulated attention and progressive refinement for further improvement. Extensive experiments demonstrate that our model achieves advanced performance in flat and nested NER, achieving a new state-of-the-art F1 score of 80.74 on the GENIA dataset and 72.38 on the WeiboNER dataset. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

ON A NOVEL UCP RESULT AND ITS APPLICATION TO INVERSE CONDUCTIVE SCATTERING

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Diao, Huaian Fei, Xiaoxu Liu, Hongyu School of Mathematics Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China School of Mathematics and Statistics Central South University Changsha410083 China Department of Mathematics City University of Hong Kong Kowloon Hong Kong

In this paper, we derive a novel Unique Continuation Principle (UCP) for a system of second-order elliptic PDEs and apply it to investigate inverse problems in conductive scattering. The UCP relaxes the typical assumptions imposed on the domain or boundary with certain interior transmission conditions. This is motivated by the study of the associated inverse scattering problem and enables us to establish several novel unique identifiability results for the determination of generalized conductive scatterers using a single far-field pattern, significantly extending the results in [15, 21]. A key technical advancement in our work is the combination of Complex Geometric Optics (CGO) techniques from [15, 21] with the Fourier expansion method to microlocally analyze corner singularities and their implications for inverse problems. We believe that the methods developed can have broader applications in other contexts. © 2024, CC BY.

关键词： Inverse problems

DK-STN: A Domain knowledge Embedded Spatio-Temporal Network Model for MJO Forecast

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Li, Hongliang Zhang, Nong Xu, Zhewen Li, Xiang Liu, Changzheng Zhao, Chongbo Wu, Jie College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun130012 China China Meteorological Administration Key Laboratory for Climate Prediction Studies National Climate Center Beijing100081 China

Understanding and predicting the Madden-Julian Oscillation (MJO) is fundamental for precipitation forecasting and disaster prevention. To date, long-term and accurate MJO prediction has remained a challenge for researchers. Conventional MJO prediction methods using Numerical Weather Prediction (NWP) are resource-intensive, time-consuming, and highly unstable. While existing Artificial Neural Network (ANN) methods save resources and speed forecasting, their accuracy never reaches the 28 days predicted by the state-of-the-art NWP method, i.e., the ECMWF, since neural networks cannot handle climate data effectively. In this paper, we present a Domain knowledge Embedded Spatio-Temporal Network (DK-STN), a stable neural network model for accurate and efficient MJO forecasting. It combines the benefits of NWP and ANN methods and successfully improves the forecast accuracy of ANN methods while maintaining a high level of efficiency and stability. We begin with a spatial-temporal network (STN) and embed domain knowledge in it using two key methods: (i) applying a domain knowledge enhancement method and (ii) integrating a domain knowledge processing method into network training. We evaluated DK-STN with the 5th generation of ECMWF reanalysis (ERA5) data and compared it with ECMWF. Given 7 days of climate data as input, DK-STN can generate reliable forecasts for the following 28 days in 1-2 seconds, with an error of only 2-3 days in different seasons. DK-STN significantly exceeds ECMWF in that its forecast accuracy is equivalent to ECMWF's, while its efficiency and stability are significantly superior. © 2023, The Authors. All rights reserved.

关键词： Weather forecasting

Causality-inspired Unsupervised Domain Adaptation with Target Style Imitation for Medical Image Segmentation

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Song, Jincai Chen, Haipeng Lyu, Yingda Nie, Weizhi Liu, An-An Jilin University College of Computer Science and Technology Jilin Changchun130012 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin Changchun130012 China Jilin University Public Computer Education and Research Center Jilin Changchun130012 China Tianjin University School of Electrical and Information Engineering Tianjin300072 China

Deep learning performance may decrease substantially with unseen heterogeneous data. While most unsupervised domain adaptation (UDA) methods seek to address this through image alignment, they often ignore uncertainty style fluctuations within the target domain. When testing image styles vary in both direction and intensity, such models may fail to adapt. Furthermore, existing UDA methods tend to over-reliance on domain-level entire feature alignment, resulting in potentially over-exploiting semantic content-independent cues (e.g., intensity) as shortcut features. To address these limitations, this paper introduces an innovative and model-agnostic Causality-inspired Representation Learning Based on Target Style Imitation method for UDA. Specifically, we propose a novel Target Style Imitation (TSI) data augmentation approach to diversify the training data and align training and unseen target testing image styles. TSI constructs a Gaussian distribution for the target domain style and simulates unseen testing style variations through random sampling. Additionally, inspired by the stable and generalizable causal mechanism, we propose Causality-inspired Representation Learning (CRL) based on TSI method to enforce feature representations to adhere to causal properties (i.e., Separation and Independence) essential for robust UDA, thus fostering the model to focus on the domain-invariant semantic features. Our method surpasses state-of-the-art methods on two cross-modality medical image segmentation datasets. © 1991-2012 IEEE.

关键词： Semantic Segmentation

Unknown Task Selection and Worker Recruitment Using Two-Stage Multi-Armed Bandit in Crowdsensing

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Song, Haoyuan Li, Peng Du, Rui Yu, Hai Huang, Weiyi Nie, Lei Bao, Haizhou Liu, Qin Wuhan University of Science and Technology School of Computer Science and Technology Wuhan430065 China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China Hubei Polytechnic University School of Computer Huangshi435003 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China

Mobile Crowdsensing (MCS) faces significant challenges in selecting tasks with expected high revenue and recruiting workers with expected high qualities to maximize overall utility. Existing approaches often assume the revenue of posting tasks or the quality of workers is determined, which limits their practical applicability. This paper tackles these challenges by modeling the long-term multi-task, multi-worker selection problem as a Two-Stage Multi-Armed Bandit (TS-MAB) problem under uncertainty. In each round, the MCS platform selects a long-term task from a pool and recruits the necessary workers, determining payments accordingly. We model the task selection phase as a MAB problem, and the worker recruitment phase, influenced by the task selection, as a Combinatorial MAB (CMAB) problem. We propose an extended Upper Confidence Bound (UCB)-based strategy and develop an incentive mechanism based on Auction theory, combined with TS-MAB (i.e., ATS-MAB), for unknown task selection and worker recruitment. Our mechanism theoretically guarantees truthfulness and individual rationality, with a theoretical analysis of its regret bounds. Furthermore, we introduce an adaptive incentive mechanism called AATS-MAB, which improves worker recruitment and quality updates, achieving higher total sensing quality and lower regret. Extensive simulations demonstrate the effectiveness and scalability of the proposed methods. © 2014 IEEE.

关键词： Personnel selection

Task Delay and Energy Consumption Minimization for Low-altitude MEC via Evolutionary Multi-objective Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sun, Geng Ma, Weilong Li, Jiahui Sun, Zemin Wang, Jiacheng Niyato, Dusit Mao, Shiwen College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore College of Software Jilin University Changchun130012 China Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States

The low-altitude economy (LAE), driven by unmanned aerial vehicles (UAVs) and other aircraft, has revolutionized fields such as transportation, agriculture, and environmental monitoring. In the upcoming six-generation (6G) era, UAV-assisted mobile edge computing (MEC) is particularly crucial in challenging environments such as mountainous or disaster-stricken areas. The computation task offloading problem is one of the key issues in UAV-assisted MEC, primarily addressing the trade-off between minimizing the task delay and the energy consumption of the UAV. In this paper, we consider a UAV-assisted MEC system where the UAV carries the edge servers to facilitate task offloading for ground devices (GDs), and formulate a calculation delay and energy consumption multi-objective optimization problem (CDECMOP) to simultaneously improve the performance and reduce the cost of the system. Then, by modeling the formulated problem as a multi-objective Markov decision process (MOMDP), we propose a multi-objective deep reinforcement learning (DRL) algorithm within an evolutionary framework to dynamically adjust the weights and obtain non-dominated policies. Moreover, to ensure stable convergence and improve performance, we incorporate a target distribution learning (TDL) algorithm. Simulation results demonstrate that the proposed algorithm can better balance multiple optimization objectives and obtain superior non-dominated solutions compared to other methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

Elucidating Spatial Complex Structures from Mass Spectrometry Imaging with Deep Multimodal Model 1

学校读者我要写书评

暂无评论

Elucidating Spatial Complex Structures from Mass Spectrometr...

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Cui, Jiangnan Xia, Junjie Li, Xuan Wang, Yan Qiu, Fufang Xu, Yaochen Xu, Keren Zuo, Chunman School of Computer Science and Technology Institute of Artificial Intelligence Donghua University Shanghai China College of Computer Science and Technology Jilin University Changchun China Huashan Hospital Department of Neurosurgery Shanghai China Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences Cas Key Laboratory of Systems Biology Shanghai China Institute of Artificial Intelligence Donghua University Shanghai China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China

ISBN: (纸本)9798350358780

Spatial mass spectrometry imaging (SMSI) technology has enabled the characterization of biomolecule patterns within the tissue microenvironment, yet its analyses suffer from substantial noise. The lack of effective methods for exploiting multi-view features (e.g., spatial location) has hindered their elucidation ability for tissue heterogeneity. Here, we propose MSG, a multimodal modal that integrates histology, spatial location, and MSI data, in deciphering tissue structure by graph neural network. Specifically, MSG learns low-dimensional representations by aggregating histomorphological features from neighboring tiles via graph attention autoencoder. MSG outperforms other methods in identifying spatial domains and denoising data. The subsequent domain-guided differential expression analysis of the denoised data enables the identification of ions with significantly enriched patterns within the recognized domains. MSG exhibits its versatility in handling SMSI data from various platforms. © 2023 IEEE.

关键词： Data integration