检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Li, Hongliang Zhao, Hairui Sun, Ting Li, Xiang Xu, Haixiao Li, Keqin College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education Changchun China High Performance Computing Center Jilin University Changchun China Department of Computer Science State University of New York New PaltzNY12561 United States

Distributed deep learning frameworks facilitate large deep learning workloads. These frameworks support sharing one GPU device among multiple jobs to improve resource utilization. Modern deep learning training jobs consume a large amount of GPU memory. Despite that, sharing GPU memory among jobs is still possible because a training job has iterative steps that its memory usage fluctuates over time. However, resource sharing also introduces the risk of job performance degradation. Colocated jobs sharing a GPU device may suffer from different levels of interference, mainly caused by memory oversharing. How to improve resource utilization while maintaining good job performance is a novel challenge for job placement strategies. This paper studies the job placement problem. We propose an opportunistic memory sharing model to describe the time-varying job memory requirements. Based on this model, we introduce an Opportunistic Job Placement Problem (OJPP) for shared GPU clusters that seek job placement configurations using a minimum number of GPU devices and guarantee user-defined performance requirements at the same time. We propose a greedy algorithm and a heuristic algorithm with computational complexities of O(n log n) and O(n2 log n), respectively, to solve the problem. We also propose an online adjustment algorithm with the computational complexity of O(n log n) to perform updates to job placement configurations in runtime. A machine-learning-based interference prediction method is used to prepare accurate interference estimations. Extensive experiments are conducted on a GPU cluster to verify the correctness and effectiveness of our algorithms. Compared with standalone training jobs on dedicated clusters, the proposed approach reduces resource consumption by 46% in a shared cluster, while guaranteeing over 92.97% of the job performance, in terms of average job completion time. © 2023, The Authors. All rights reserved.

关键词： computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection

arXiv

引用

arXiv 2022年

作者： Yang, Zhiwei Ma, Jing Chen, Hechang Lin, Hongzhan Luo, Ziyang Chang, Yi College of Computer Science and Technology Jilin University Changchun China Department of Computer Science Hong Kong Baptist University Hong Kong School of Artificial Intelligence Jilin University China International Center of Future Science Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China

Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances. However, they often tailor automated solutions on manual fact-checked reports, suffering from limited news coverage and debunking delays. When a piece of news has not yet been fact-checked or debunked, certain amounts of relevant raw reports are usually disseminated on various media outlets, containing the wisdom of crowds to verify the news claim and explain its verdict. In this paper, we propose a novel Coarse-to-fine Cascaded Evidence-Distillation (CofCED) neural network for explainable fake news detection based on such raw reports, alleviating the dependency on fact-checked ones. Specifically, we first utilize a hierarchical encoder for web text representation, and then develop two cascaded selectors to select the most explainable sentences for verdicts on top of the selected top-K reports in a coarse-to-fine manner. Besides, we construct two explainable fake news datasets, which are publicly available. Experimental results demonstrate that our model significantly outperforms state-of-the-art baselines and generates high-quality explanations from diverse evaluation perspectives. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

CellMirror: Deciphering Cell Populations from Spatial Transcriptomics Data by Interpretable Contrastive Learning 1

CellMirror: Deciphering Cell Populations from Spatial Transc...

引用

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

作者： Xia, Junjie Cui, Jiangnan Huang, Zhenyu Zhang, Shuangquan Yao, Fang Zhang, Yijian Zuo, Chunman Institute of Artificial Intelligence Donghua University Department of Applied Mathematics Shanghai China College of Computer Science and Technology Jilin University Changchun China School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing China Institute of Maternal and Child Medicine Southern Medical University Affiliated Shenzhen Maternity and Child Healthcare Hospital Shenzhen China Xinhua Hospital Affiliated Shanghai Jiao Tong University of Medicine Department of General Surgery Shanghai China Institute of Artificial Institute Donghua University Shanghai China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China

ISBN: (纸本)9798350358780

Spatial transcriptomics (ST) has enabled us elucidating tumor microenvironments, however, the technological limitations without single-cell resolution severely hinder its application. Here, we propose CellMirror, an interpretable contrastive learning model to decipher heterogeneous cell populations in ST data by single-cell RNA-sequencing (scRNA-seq) data. Specifically, CellMirror learns the disentangled shared (representing biological variations in both data) and salient features (specific to ST data) by two contrastive variational encoders, while constructing the relations between genes and features by a shared linear decoder. In various cancer samples, CellMirror outperforms other tools in learning common features for label transfer, and interpretation of features. Particularly, in breast cancer studies, CellMirror detects finer domains in ST data missed by other methods, and is robust to dissect cell populations in ST data using independent scRNA-seq data. These results demonstrate applications of CellMirror in interpreting the complex tumor structure in ST data by integrating scRNA-seq data. © 2023 IEEE.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

Convergence-Aware Optimal Checkpointing for Exploratory Deep Learning Training Jobs

SSRN

引用

SSRN 2024年

作者： Li, Hongliang Wang, Zichen Zhao, Hairui Zhang, Meng Li, Xiang Xu, Haixiao College of Computer Science and Technology Jilin University Qianjin street 2699 Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education Qianjin street 2699 Jilin Changchun130012 China High Performance Computing Center Qianjin street 2699 Jilin Changchun130012 China

Training Deep Learning (DL) models are becoming more time-consuming, thus interruptions to the training processes are inevitable. Existing fault-tolerant work adopted checkpoint/recovery mechanism from traditional HPC platforms that makes periodical persistent copies of model states to save execution progress. These checkpoints have fixed time intervals that they are evenly placed across the training. We can obtain an optimal checkpointing interval for an HPC job with the precondition that the progress of a job is proportional to its execution time. Unfortunately, it is not the case in DL model training where a DL training job yields diminishing returns across its lifetime. It makes the early progress of a DL training job more valuable than the later ones. Even placement of checkpoints would either increase the risks in the early stages or waste resources overprotecting the latter stages. Meanwhile, the issue can get amplified for exploratory training jobs, where early terminations are common. Moreover, in data parallelism, the state-of-art quality-driven scheduling strategies allocate more resources for the early stages of a job than the later ones to accelerate the training progress which further amplifies the issue. This paper introduces a novel checkpointing interval problem for exploratory DL training jobs based on model convergence progress. We present COCI, an approach to compute optimal checkpointing configuration for a DL training job, minimizing the fault-tolerant overhead, including checkpointing cost and recovery cost. We implement COCI based on state-of-art iteration-level checkpointing mechanism, as a pluggable module compatible with PyTorch. COCI requires no extra user input. We conduct comprehensive evaluations with real DL application setups. The experimental results show that COCI reduces up to 40.18% fault-tolerant overhead compared to existing state-of-the-art DL fault-tolerant methods in serial scenario, 57.26% in data parallel scenario and 63.8

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A hybrid algorithm of minimum spanning tree and nearest neighbor for classifying human cancers

A hybrid algorithm of minimum spanning tree and nearest neig...

引用

International Conference on Advanced Computer Theory and engineering, ICACTE

作者： Chunbao Zhou Liming Wan Yanchun Liang College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun China Research Institute on General Development and Evaluation of Equipment EAAF of PLA Beijing China

ISBN: (纸本)9781424465392

Classification and prediction of different cancers based on gene expression profiles are important for cancer diagnosis, cancer treatment and medication discovery. The k nearest neighbor algorithm (k-NN) is one easy and efficient machine learning method for cancer classification and the parameter k is crucial. In this paper, we integrate minimum spanning tree (MST) and k nearest neighbor algorithm (k-NN) for cancer classification. The MST is designed for the selection of parameter k and the nearest neighbors for k-NN. Firstly we build a minimum spanning tree (MST) based on Euclidean distance between each two samples for gene expression data only including one unknown class sample. Secondly for unknown class sample in the gene expression data, we find the connected samples and then apply majority vote principle. Thirdly if there are tied votes then we expend the connected samples with the nearest neighbors for unknown class sample until all the samples are expended or the class for unknown sample is obtained. This hybrid algorithm is referred to as MSTNN. The hybrid algorithm MSTNN is compared with k-NN and other 3 existing classification algorithms on CNS dataset, Colon dataset and Lung dataset, 3 binary class gene expression datasets and 3 multi-class gene expression datasets: Leukemia1, Leukemia2, and Leukemia3 involving human cancers. The MSTNN algorithm improves 5.65% better than k-NN on average LOOCV accuracy and 13.80% better than k-NN on testing datasets classification average accuracy, and achieves the best performance in all the 5 algorithms. The results demonstrate that the proposed MSTNN algorithm is feasible to classify human cancers.

关键词： Classification algorithms Artificial neural networks Niobium Lungs Colon Support vector machines Cancer

来源：评论

学校读者我要写书评

暂无评论

Joint Power and 3D Trajectory Optimization for UAV-enabled Wireless Powered Communication Networks with Obstacles

arXiv

引用

arXiv 2023年

作者： Pan, Hongyang Liu, Yanheng Sun, Geng Fan, Junsong Liang, Shuang Yuen, Chau The College of Computer Science and Technology Jilin University Changchun130012 China Pillar Singapore University of Technology and Design 487372 Singapore The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China The School of Information Science and Technology Northeast Normal University Changchun130024 China

Unmanned aerial vehicle (UAV)-enabled wireless powered communication networks (WPCNs) are promising technologies in 5G/6G wireless communications, while there are several challenges about UAV power allocation and scheduling to enhance the energy utilization efficiency, considering the existence of obstacles. In this work, we consider a UAV-enabled WPCN scenario that a UAV needs to cover the ground wireless devices (WDs). During the coverage process, the UAV needs to collect data from the WDs and charge them simultaneously. To this end, we formulate a joint-UAV power and three-dimensional (3D) trajectory optimization problem (JUPTTOP) to simultaneously increase the total number of the covered WDs, increase the time efficiency, and reduce the total flying distance of UAV so as to improve the energy utilization efficiency in the network. Due to the difficulties and complexities, we decompose it into two sub optimization problems, which are the UAV power allocation optimization problem (UPAOP) and UAV 3D trajectory optimization problem (UTTOP), respectively. Then, we propose an improved non-dominated sorting genetic algorithm-II with K-means initialization operator and Variable dimension mechanism (NSGA-II-KV) for solving the UPAOP. For UTTOP, we first introduce a pretreatment method, and then use an improved particle swarm optimization with Normal distribution initialization, Genetic mechanism, Differential mechanism and Pursuit operator (PSO-NGDP) to deal with this sub optimization problem. Simulation results verify the effectiveness of the proposed strategies under different scales and settings of the networks. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A Multi-Agent Deep Reinforcement Learning Method for Fully Noisy Observations

SSRN

引用

SSRN 2023年

作者： Wang, Kaiyu Zhang, Menglin Qu, Bohao Wang, Xianchang College of Computer Science and Technology Jilin University Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin Changchun130012 China School of Artificial Intelligence Jilin University Jilin Changchun130012 China Chengdu Kestrel Artificial Intelligence Institute Chengdu611730 China

Multi-agent reinforcement learning (MARL) algorithms have achieved great breakthroughs in many aspects. The MARL algorithms can learn effective policies in ideal simulation environments. But different from the ideal simulation environments, noise is unavoidable in the real world. MARL algorithms need to learn effective policies in unavoidable fully noisy environments. In this paper, we consider a challenging multi-agent reinforcement learning problem: All agents cannot observe any noiseless observations from environments during the whole training process and MARL algorithms cannot learn effective policies in these fully noisy observation environments. To solve this problem, we propose a method called Robust Policy Learning under Fully Noisy Observation viA DeNoising REpresentation NeTwork (PLANET), which enables MARL algorithms learning effective policies in fully noisy observation environments. The PLANET method learns the effective policy through two steps. (1) Extracting the noise characteristics and motion laws information from fully noisy observation histories. (2) Making MARL algorithms extract information from the noise characteristics and motion laws information and learn effective policies. The results of a series of exhaustive experiments show that our method can eliminate the effects of noise and learn effective policies in fully noisy observation environments. © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Implicit knowledge discovery in biomedical ontologies: Computing interesting relatednesses

Implicit knowledge discovery in biomedical ontologies: Compu...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tian Bai Leiguang Gong Casimir A. Kulikowski Lan Huang Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China Yantai Intelligent Information Technologies Ltd. Yantai China Department of Computer Science Rutgers The State University of New Jersey Piscataway NJ USA

Ontologies, seen as effective representations for sharing and reusing knowledge, have become increasingly important in biomedicine, usually focusing on taxonomic knowledge specific to a subject. Efforts have been made to uncover implicit knowledge within large biomedical ontologies by exploring semantic similarity and relatedness between concepts. However, much less attention has been paid to another potentially helpful approach: discovering implicit knowledge across multiple ontologies of different types, such as disease ontologies, symptom ontologies, and gene ontologies. In this paper, we propose a unified approach to the problem of ontology based implicit knowledge discovery - a Multi-Ontology Relatedness Model (MORM), which includes the formation of multiple related ontologies, a relatedness network and a formal inference mechanism based on set-theoretic operations. Experiments for biomedical applications have been carried out, and preliminary results show the potential value of the proposed approach for biomedical knowledge discovery.

关键词： Biological system modeling Biomedical measurement Ontologies Arthritis Diseases

来源：评论

学校读者我要写书评

暂无评论

Dual UAV Cluster-Assisted Maritime Physical Layer Secure Communications via Collaborative Beamforming

arXiv

引用

arXiv 2024年

作者： Huang, Jiawei Wang, Aimin Sun, Geng Li, Jiahui Wang, Jiacheng Du, Hongyang Niyato, Dusit 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 Department of Electrical and Electronic Engineering Hong Kong University 999077 Hong Kong

Unmanned aerial vehicles (UAVs) can be utilized as relay platforms to assist maritime wireless communications. However, complex channels and multipath effects at sea can adversely affect the quality of UAV transmitted signals. Collaborative beamforming (CB) can enhance the signal strength and range to assist the UAV relay for remote maritime communications. However, due to the open nature of UAV channels, security issue requires special consideration. This paper proposes a dual UAV cluster-assisted system via CB to achieve physical layer security in maritime wireless communications. Specifically, one UAV cluster forms a maritime UAV-enabled virtual antenna array (MUVAA) relay to forward data signals to the remote legitimate vessel, and the other UAV cluster forms an MUVAA jammer to send jamming signals to the remote eavesdropper. In this system, we formulate a secure and energy-efficient maritime communication multi-objective optimization problem (SEMCMOP) to maximize the signal-to-interference-plus-noise ratio (SINR) of the legitimate vessel, minimize the SINR of the eavesdropping vessel and minimize the total flight energy consumption of UAVs. Since the SEMCMOP is an NP-hard and large-scale optimization problem, we propose an improved swarm intelligence optimization algorithm with chaotic solution initialization and hybrid solution update strategies to solve the problem. Simulation results indicate that the proposed algorithm outperforms other comparison algorithms, and it can achieve more efficient signal transmission by using the CB-based method. Copyright © 2024, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

TemporalPaD: a reinforcement-learning framework for temporal feature representation and dimension reduction

arXiv

引用

arXiv 2024年

作者： Mu, Xuechen Huang, Zhenyu Li, Kewei Zhang, Haotian Wang, Xiuli Fan, Yusi Zhang, Kai Zhou, Fengfeng Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun130012 China School of Mathematics Jilin University Jilin Changchun130012 China College of computer Science and Technology Jilin University Jilin Changchun130012 China School of Biology and Engineering Guizhou Medical University Guizhou Guiyang550025 China

Recent advancements in feature representation and dimension reduction have highlighted their crucial role in enhancing the efficacy of predictive modeling. This work introduces TemporalPaD, a novel end-to-end deep learning framework designed for temporal pattern datasets. TemporalPaD integrates reinforcement learning (RL) with neural networks to achieve concurrent feature representation and feature reduction. The framework consists of three cooperative modules: a Policy Module, a Representation Module, and a Classification Module, structured based on the Actor-Critic (AC) framework. The Policy Module, responsible for dimensionality reduction through RL, functions as the actor, while the Representation Module for feature extraction and the Classification Module collectively serve as the critic. We comprehensively evaluate TemporalPaD using 29 UCI datasets, a well-known benchmark for validating feature reduction algorithms, through 10 independent tests and 10-fold cross-validation. Additionally, given that TemporalPaD is specifically designed for time series data, we apply it to a real-world DNA classification problem involving enhancer category and enhancer strength. The results demonstrate that TemporalPaD is an efficient and effective framework for achieving feature reduction, applicable to both structured data and sequence datasets. The source code of the proposed TemporalPaD is freely available as supplementary material to this article and at http://***/supp/. © 2024, CC BY-NC-ND.

关键词： Reinforcement learning

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：