检索结果-内蒙古大学图书馆

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

学校读者我要写书评

暂无评论

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

Interference-Aware Opportunistic Job Placement for Shared Distributed Deep Learning Clusters

学校读者我要写书评

暂无评论

SSRN

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

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

学校读者我要写书评

暂无评论

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

Pathological brain detection based on online sequential extreme learning machine

学校读者我要写书评

暂无评论

Pathological brain detection based on online sequential extr...

IEEE International Conference on Progress in Informatics and Computing (PIC)

作者： Siyuan Lu Hainan Wang Xueyan Wu Shuihua Wang School of Computer Science and Technology Nanjing Normal University Nanjing Jiangsu China State Key Lab of CAD & CG Zhejiang University Hangzhou Zhejiang China Key laboratory of symbolic computation and knowledge engineering of ministry of education Jilin University Changchun Jilin China Key Laboratory of Statistical information technology and data mining State Statistics Bureau Chengdu Sichuan China Department of Electrical Engineering CUNY New York NY USA

ISBN: (纸本)9781509034857

Magnetic resonance imaging (MRI) is a kind of imaging modality, which offers clearer images of soft tissues than computed tomography (CT). It is especially suitable for brain disease detection. It is beneficial to detect diseases automatically and accurately. We proposed a pathological brain detection method based on brain MR images and online sequential extreme learning machine. First, seven wavelet entropies (WE) were extracted from each brain MR image to form the feature vector. Then, an online sequential extreme learning machine (OS-ELM) was trained to differentiate pathological brains from the healthy controls. The experiment results over 132 brain MRIs showed that the proposed approach achieved a sensitivity of 93.51%, a specificity of 92.22%, and an overall accuracy of 93.33%, which suggested that our method is effective.

关键词： Entropy Discrete wavelet transforms Feature extraction Pathology Training Magnetic resonance imaging Diseases

Convergence-Aware Optimal Checkpointing for Exploratory Deep Learning Training Jobs

学校读者我要写书评

暂无评论

SSRN

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

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

学校读者我要写书评

暂无评论

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

Describing the semantic relation of the deep web query interfaces using ontology extended LAV

学校读者我要写书评

暂无评论

Journal of Software

Journal of Software 2010年第1期5卷 89-98页

作者： Liang, Hao Zuo, Wan-Li Ren, Fei Department of Computer Science and Technology Jilin University Jilin Changchun China Department of Information Changchun Taxation College Jilin Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun China

The key element in a Deep Web information fusion system is the data source modeling problem, which is the determinant technical factor of the whole system. The query interfaces provided by the Deep Web are the clues to disclose the hidden schemas. But the complicated semantic relationships in the query interfaces lead to the lower generality and ability of local as view (LAV) method in the traditional information fusion system. An approach of extracting attributes and semantic relationships from the interfaces utilizing Ontology is present in this paper, and WordNet is introduced as an Ontology instrument. The semantic relationships between semantic related attributes are evaluated by the WordNet. The meaningless attributes are instantiated by instance information embedded in the interfaces. A semantic matrix is generated and used to evaluate the semantic related groups in the specific domains. The expression ability of LAV is extended by the mapping and matching mechanism based on the semantic related groups. The experiment is carried out on the famous dataset, and the results show the efficiency of Ontology extended LAV of building mappings between local schemas and mediator schema. © 2010 ACADEMY PUBLISHER.

关键词： Ontology

Mining data records based on ontology evolution for deep web

学校读者我要写书评

暂无评论

Mining data records based on ontology evolution for deep web

International Conference on Computer engineering and Technology, ICCET

作者： Wen Zhang Kerui Chen Fan Zhang College of Information Engineering Zhongzhou University Zhengzhou China College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Changchun China

ISBN: (纸本)9781424463473;9781424463497;9781424463503

Currently, the research for the extraction of information in deep web is pretty active. Although many researchers already adopted ontology in the data extraction, many problems still exist. This paper proposed an ontology evolution based method for mining in the data area. Not only will this method solve the problem when the website only consists of one record, but it also can identify he meaning of data that has no labels. With the evolution of ontology, the extraction of data records is being more accurate. Experiments indicate that this method could improve the accuracy and efficiency of data extraction.

关键词： Data mining Ontologies Entropy Educational institutions knowledge engineering Web pages Data engineering Random processes Computer science Educational technology

GEOM-GCN: Geometric graph convolutional networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Pei, Hongbin Wei, Bingzhe Chang, Kevin Chen-Chuan Lei, Yu Yang, Bo College of Computer Science and Technology Jilin University China Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign United States Department of Computer Science University of Illinois at Urbana-Champaign United States Department of Computing Hong Kong Polytechnic University Hong Kong Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education China

Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs. Few studies have noticed the weaknesses from different perspectives. From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses. The behind basic idea is the aggregation on a graph can benefit from a continuous space underlying the graph. The proposed aggregation scheme is permutation-invariant and consists of three modules, node embedding, structural neighborhood, and bi-level aggregation. We also present an implementation of the scheme in graph convolutional networks, termed Geom-GCN, to perform transductive learning on graphs. Experimental results show the proposed Geom-GCN achieved state-of-the-art performance on a wide range of open datasets of graphs. Copyright © 2020, The Authors. All rights reserved.

关键词： Graphic methods